CVE-2026-57860 (GCVE-0-2026-57860)

Vulnerability from cvelistv5 – Published: 2026-07-17 16:16 – Updated: 2026-07-20 17:45
VLAI
Title
ForgeCode Arbitrary Code Execution via Unvetted .mcp.json in Untrusted Repository
Summary
ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: ['-c', 'touch /tmp/pwned']). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user's privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode.
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-17 16:45 UTC
CWE
  • CWE-829 - Inclusion of Functionality from Untrusted Control Sphere
Impacted products
Vendor Product Version CPE status
tailcallhq forgecode Affected: 2.11.1 (git)
guessed Create a notification for this product.
Date Public
2026-07-17 00:00
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-57860",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-17T16:45:24.963875Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-17T16:45:31.572Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/tailcallhq/forgecode/issues/3022"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "affected",
          "packageURL": "pkg:npm/forgecode",
          "product": "forgecode",
          "vendor": "tailcallhq",
          "versions": [
            {
              "status": "affected",
              "version": "2.11.1",
              "versionType": "git"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Saad ELHARAJ (SAAITAAMAA)"
        }
      ],
      "datePublic": "2026-07-17T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository\u0027s .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: [\u0027-c\u0027, \u0027touch /tmp/pwned\u0027]). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user\u0027s privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.4,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 7.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-829",
              "description": "Inclusion of Functionality from Untrusted Control Sphere",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-20T17:45:55.116Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Issue",
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/tailcallhq/forgecode/issues/3022"
        },
        {
          "name": "GitHub Issue",
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/tailcallhq/forgecode/issues/3252"
        },
        {
          "name": "Product",
          "tags": [
            "product"
          ],
          "url": "https://github.com/tailcallhq/forgecode"
        },
        {
          "name": "Patch Commit",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/tailcallhq/forgecode/commit/68ca3a3a26c73c38a700453d3d021b5bbdc15dbd"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/forgecode-arbitrary-code-execution-via-unvetted-mcp-json-in-untrusted-repository"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "ForgeCode Arbitrary Code Execution via Unvetted .mcp.json in Untrusted Repository",
      "x_generator": {
        "engine": "vulncheck"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-57860",
    "datePublished": "2026-07-17T16:16:09.573Z",
    "dateReserved": "2026-06-25T18:48:00.283Z",
    "dateUpdated": "2026-07-20T17:45:55.116Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-57860",
      "date": "2026-09-15",
      "epss": "0.00196",
      "percentile": "0.09558"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-57860\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-07-17T17:17:16.777\",\"lastModified\":\"2026-07-17T18:28:39.220\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository\u0027s .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: [\u0027-c\u0027, \u0027touch /tmp/pwned\u0027]). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user\u0027s privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode.\"}],\"affected\":[{\"source\":\"disclosure@vulncheck.com\",\"affectedData\":[{\"vendor\":\"tailcallhq\",\"product\":\"forgecode\",\"defaultStatus\":\"affected\",\"packageURL\":\"pkg:npm/forgecode\",\"versions\":[{\"version\":\"2.11.1\",\"versionType\":\"git\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/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\":8.4,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"ACTIVE\",\"vulnConfidentialityImpact\":\"HIGH\",\"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\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\",\"baseScore\":7.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-07-17T16:45:24.963875Z\",\"id\":\"CVE-2026-57860\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-829\"}]}],\"references\":[{\"url\":\"https://github.com/tailcallhq/forgecode\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/tailcallhq/forgecode/commit/68ca3a3a26c73c38a700453d3d021b5bbdc15dbd\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/tailcallhq/forgecode/issues/3022\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/tailcallhq/forgecode/issues/3252\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/forgecode-arbitrary-code-execution-via-unvetted-mcp-json-in-untrusted-repository\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/tailcallhq/forgecode/issues/3022\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-57860\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-07-17T16:45:24.963875Z\"}}}], \"references\": [{\"url\": \"https://github.com/tailcallhq/forgecode/issues/3022\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-07-17T16:45:16.883Z\"}}], \"cna\": {\"title\": \"ForgeCode Arbitrary Code Execution via Unvetted .mcp.json in Untrusted Repository\", \"source\": {\"discovery\": \"UNKNOWN\"}, \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Saad ELHARAJ (SAAITAAMAA)\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"Safety\": \"NOT_DEFINED\", \"version\": \"4.0\", \"Recovery\": \"NOT_DEFINED\", \"baseScore\": 8.4, \"Automatable\": \"NOT_DEFINED\", \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"valueDensity\": \"NOT_DEFINED\", \"vectorString\": \"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N\", \"providerUrgency\": \"NOT_DEFINED\", \"userInteraction\": \"ACTIVE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnerabilityResponseEffort\": \"NOT_DEFINED\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.8, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"vendor\": \"tailcallhq\", \"product\": \"forgecode\", \"versions\": [{\"status\": \"affected\", \"version\": \"2.11.1\", \"versionType\": \"git\"}], \"packageURL\": \"pkg:npm/forgecode\", \"defaultStatus\": \"affected\"}], \"datePublic\": \"2026-07-17T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/tailcallhq/forgecode/issues/3022\", \"name\": \"GitHub Issue\", \"tags\": [\"issue-tracking\"]}, {\"url\": \"https://github.com/tailcallhq/forgecode/issues/3252\", \"name\": \"GitHub Issue\", \"tags\": [\"issue-tracking\"]}, {\"url\": \"https://github.com/tailcallhq/forgecode\", \"name\": \"Product\", \"tags\": [\"product\"]}, {\"url\": \"https://github.com/tailcallhq/forgecode/commit/68ca3a3a26c73c38a700453d3d021b5bbdc15dbd\", \"name\": \"Patch Commit\", \"tags\": [\"patch\"]}, {\"url\": \"https://www.vulncheck.com/advisories/forgecode-arbitrary-code-execution-via-unvetted-mcp-json-in-untrusted-repository\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository\u0027s .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: [\u0027-c\u0027, \u0027touch /tmp/pwned\u0027]). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user\u0027s privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-829\", \"description\": \"Inclusion of Functionality from Untrusted Control Sphere\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-07-20T17:45:55.116Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-57860\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-07-20T17:45:55.116Z\", \"dateReserved\": \"2026-06-25T18:48:00.283Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-07-17T16:16:09.573Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.

Loading…

Detection rules are retrieved from Rulezet.

Loading…

Loading…

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.


Loading…