GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

CVE-2026-45374 (GCVE-0-2026-45374)

Vulnerability from cvelistv5 – Published: 2026-05-28 17:26 – Updated: 2026-05-30 02:04
VLAI
Title
CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files
Summary
CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.
Severity
9.6 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-30 02:04 UTC
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
References
Impacted products
Vendor Product Version CPE status
Hmbown CodeWhale Affected: < 0.8.26
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-45374",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-30T02:04:28.787540Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-30T02:04:52.694Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "CodeWhale",
          "vendor": "Hmbown",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.8.26"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.6,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-28T17:29:11.005Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4"
        },
        {
          "name": "https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26"
        }
      ],
      "source": {
        "advisory": "GHSA-72w5-pf8h-xfp4",
        "discovery": "UNKNOWN"
      },
      "title": "CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-45374",
    "datePublished": "2026-05-28T17:26:42.979Z",
    "dateReserved": "2026-05-12T00:51:29.086Z",
    "dateUpdated": "2026-05-30T02:04:52.694Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-45374",
      "date": "2026-09-17",
      "epss": "0.0026",
      "percentile": "0.17933"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-45374\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-28T18:16:35.843\",\"lastModified\":\"2026-06-17T10:51:58.960\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"Hmbown\",\"product\":\"CodeWhale\",\"versions\":[{\"version\":\"\u003c 0.8.26\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\",\"baseScore\":9.6,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":6.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-05-30T02:04:28.787540Z\",\"id\":\"CVE-2026-45374\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"}]}],\"references\":[{\"url\":\"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "redhat_vex": {
      "current_release_date": "2026-05-30T08:13:05+00:00",
      "cve": "CVE-2026-45374",
      "id": "CVE-2026-45374",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-45374.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-45374\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-30T02:04:28.787540Z\"}}}], \"references\": [{\"url\": \"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-30T02:04:48.320Z\"}}], \"cna\": {\"title\": \"CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files\", \"source\": {\"advisory\": \"GHSA-72w5-pf8h-xfp4\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 9.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"Hmbown\", \"product\": \"CodeWhale\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.8.26\"}]}], \"references\": [{\"url\": \"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4\", \"name\": \"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26\", \"name\": \"https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-28T17:29:11.005Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-45374\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-30T02:04:52.694Z\", \"dateReserved\": \"2026-05-12T00:51:29.086Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-28T17:26:42.979Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.


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.