Vulnerability-Lookup

CVE-2026-76072 (GCVE-0-2026-76072)

Vulnerability from cvelistv5 – Published: 2026-08-24 17:55 – Updated: 2026-08-24 18:36

Title

Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode

Summary

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user's data.

Severity

8.3 (High)


                        
                          CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N

7.4 (High)


                        
                          CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H

SSVC

Exploitation: poc Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-24 18:35 UTC

CWE

CWE-184 - Incomplete List of Disallowed Inputs

Assigner

VulnCheck mitre root

References

5 references

URL	Tags
https://github.com/continuedev/continue	product
https://github.com/continuedev/continue/issues/13001	issue-tracking
https://github.com/continuedev/continue/blob/main…	technical-description
https://www.npmjs.com/package/@continuedev/cli	product
https://www.vulncheck.com/advisories/continue-cli…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version	CPE status
continuedev	continue	Affected: 0 , ≤ 1.5.47 (semver) cpe:2.3:a:continue:continue::::::node.js::*

Date Public

2026-08-24 00:00

Credits

George Chen

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-76072",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-24T18:35:13.915173Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-24T18:36:09.720Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/continuedev/continue/issues/13001"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:npm/%40continuedev/cli",
          "product": "continue",
          "repo": "https://github.com/continuedev/continue",
          "vendor": "continuedev",
          "versions": [
            {
              "lessThanOrEqual": "1.5.47",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:continue:continue:*:*:*:*:*:node.js:*:*",
                  "versionEndIncluding": "1.5.47",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "George Chen"
        }
      ],
      "datePublic": "2026-08-24T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user\u0027s data."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "HIGH",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 8.3,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "HIGH"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.4,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "NONE",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-184",
              "description": "Incomplete List of Disallowed Inputs",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-24T17:55:38.529Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/continuedev/continue"
        },
        {
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/continuedev/continue/issues/13001"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://www.npmjs.com/package/@continuedev/cli"
        },
        {
          "name": "VulnCheck Advisory: Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode"
        }
      ],
      "title": "Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-76072",
    "datePublished": "2026-08-24T17:55:38.529Z",
    "dateReserved": "2026-08-18T21:04:48.504Z",
    "dateUpdated": "2026-08-24T18:36:09.720Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-76072\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-08-24T18:17:21.233\",\"lastModified\":\"2026-08-24T19:16:58.897\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user\u0027s data.\"}],\"affected\":[{\"source\":\"disclosure@vulncheck.com\",\"affectedData\":[{\"vendor\":\"continuedev\",\"product\":\"continue\",\"defaultStatus\":\"unaffected\",\"repo\":\"https://github.com/continuedev/continue\",\"packageURL\":\"pkg:npm/%40continuedev/cli\",\"versions\":[{\"version\":\"0\",\"lessThanOrEqual\":\"1.5.47\",\"versionType\":\"semver\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X\",\"baseScore\":8.3,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"attackRequirements\":\"PRESENT\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"NONE\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"HIGH\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"NONE\",\"subAvailabilityImpact\":\"NONE\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}],\"cvssMetricV31\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H\",\"baseScore\":7.4,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.2,\"impactScore\":5.2}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-24T18:35:13.915173Z\",\"id\":\"CVE-2026-76072\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-184\"}]}],\"references\":[{\"url\":\"https://github.com/continuedev/continue\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/continuedev/continue/issues/13001\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.npmjs.com/package/@continuedev/cli\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/continuedev/continue/issues/13001\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-76072\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-24T18:35:13.915173Z\"}}}], \"references\": [{\"url\": \"https://github.com/continuedev/continue/issues/13001\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-24T18:35:27.400Z\"}}], \"cna\": {\"title\": \"Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode\", \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"George Chen\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 8.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"NONE\"}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.4, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"repo\": \"https://github.com/continuedev/continue\", \"vendor\": \"continuedev\", \"product\": \"continue\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"versionType\": \"semver\", \"lessThanOrEqual\": \"1.5.47\"}], \"packageURL\": \"pkg:npm/%40continuedev/cli\", \"defaultStatus\": \"unaffected\"}], \"datePublic\": \"2026-08-24T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/continuedev/continue\", \"tags\": [\"product\"]}, {\"url\": \"https://github.com/continuedev/continue/issues/13001\", \"tags\": [\"issue-tracking\"]}, {\"url\": \"https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://www.npmjs.com/package/@continuedev/cli\", \"tags\": [\"product\"]}, {\"url\": \"https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode\", \"name\": \"VulnCheck Advisory: Continue CLI through 1.5.47 Incomplete Destructive Command Denylist in Headless and Auto Mode\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user\u0027s data.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-184\", \"description\": \"Incomplete List of Disallowed Inputs\"}]}], \"cpeApplicability\": [{\"nodes\": [{\"negate\": false, \"cpeMatch\": [{\"criteria\": \"cpe:2.3:a:continue:continue:*:*:*:*:*:node.js:*:*\", \"vulnerable\": true, \"versionEndIncluding\": \"1.5.47\"}], \"operator\": \"OR\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-08-24T17:55:38.529Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-76072\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-24T18:36:09.720Z\", \"dateReserved\": \"2026-08-18T21:04:48.504Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-08-24T17:55:38.529Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-76072

Vulnerability from fkie_nvd - Published: 2026-08-24 18:17 - Updated: 2026-08-24 19:16

Severity

7.4 (High) - CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H

Summary

References

	URL	Tags
	disclosure@vulncheck.com	https://github.com/continuedev/continue
	disclosure@vulncheck.com	https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts
	disclosure@vulncheck.com	https://github.com/continuedev/continue/issues/13001
	disclosure@vulncheck.com	https://www.npmjs.com/package/@continuedev/cli
	disclosure@vulncheck.com	https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/continuedev/continue/issues/13001

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:npm/%40continuedev/cli",
          "product": "continue",
          "repo": "https://github.com/continuedev/continue",
          "vendor": "continuedev",
          "versions": [
            {
              "lessThanOrEqual": "1.5.47",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "source": "disclosure@vulncheck.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user\u0027s data."
    }
  ],
  "id": "CVE-2026-76072",
  "lastModified": "2026-08-24T19:16:58.897",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.4,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "NONE",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 2.2,
        "impactScore": 5.2,
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "HIGH",
          "attackRequirements": "PRESENT",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 8.3,
          "baseSeverity": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "NONE",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "NONE",
          "vulnIntegrityImpact": "HIGH",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-76072",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-08-24T18:35:13.915173Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-08-24T18:17:21.233",
  "references": [
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/continuedev/continue"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/continuedev/continue/issues/13001"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://www.npmjs.com/package/@continuedev/cli"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "url": "https://github.com/continuedev/continue/issues/13001"
    }
  ],
  "sourceIdentifier": "disclosure@vulncheck.com",
  "vulnStatus": "Received",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-184"
        }
      ],
      "source": "disclosure@vulncheck.com",
      "type": "Secondary"
    }
  ]
}

GHSA-XQR4-4XJV-5J7Q

Vulnerability from github – Published: 2026-08-24 18:31 – Updated: 2026-08-24 18:31

Details

The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /, ~, ~/, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user's data.

Severity

7.4 (High)


                  
                    CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H

8.3 (High)


                  
                    CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-76072"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-184"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-08-24T18:17:21Z",
    "severity": "HIGH"
  },
  "details": "The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user\u0027s data.",
  "id": "GHSA-xqr4-4xjv-5j7q",
  "modified": "2026-08-24T18:31:57Z",
  "published": "2026-08-24T18:31:57Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-76072"
    },
    {
      "type": "WEB",
      "url": "https://github.com/continuedev/continue/issues/13001"
    },
    {
      "type": "WEB",
      "url": "https://github.com/continuedev/continue"
    },
    {
      "type": "WEB",
      "url": "https://github.com/continuedev/continue/blob/main/packages/terminal-security/src/evaluateTerminalCommandSecurity.ts"
    },
    {
      "type": "WEB",
      "url": "https://www.npmjs.com/package/@continuedev/cli"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/continue-cli-through-incomplete-destructive-command-denylist-in-headless-and-auto-mode"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.

Action not permitted

CVE-2026-76072 (GCVE-0-2026-76072)

FKIE_CVE-2026-76072

GHSA-XQR4-4XJV-5J7Q

Tags

Sightings

Nomenclature