CVE-2026-114386 (GCVE-0-2026-114386)
Vulnerability from cvelistv5
Published
2026-10-21 12:39
Modified
2026-10-21 19:55
Severity ?
6.3 (Medium) - CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N
4.8 (Medium) - CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
CWE
  • CWE-770 - Allocation of Resources Without Limits or Throttling
Summary
Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools.
References
Impacted products
Vendor Product Version
pydantic pydantic-ai-harness Version: 0   ≤
Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-114386",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-10-21T19:55:43.280737Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-10-21T19:55:49.371Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/pydantic-ai-harness",
          "product": "pydantic-ai-harness",
          "repo": "https://github.com/pydantic/pydantic-ai",
          "vendor": "pydantic",
          "versions": [
            {
              "lessThan": "0.59.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "CBF"
        }
      ],
      "datePublic": "2026-10-15T20:54:31.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 6.3,
            "baseSeverity": "MEDIUM",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "LOW",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "LOW"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 4.8,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-770",
              "description": "Allocation of Resources Without Limits or Throttling",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-21T12:39:43.886Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "issue-tracking",
            "patch"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/pull/10362"
        },
        {
          "tags": [
            "patch"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949"
        },
        {
          "name": "pydantic-ai-harness v2.59.0 Release Notes",
          "tags": [
            "release-notes"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://pypi.org/project/pydantic-ai-harness/0.59.0/"
        },
        {
          "name": "VulnCheck Advisory: Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-call-limit-bypass-via-run-code"
        }
      ],
      "title": "Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-114386",
    "datePublished": "2026-10-21T12:39:43.886Z",
    "dateReserved": "2026-10-21T11:46:40.374Z",
    "dateUpdated": "2026-10-21T19:55:49.371Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-114386\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-10-21T19:55:43.280737Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-10-21T19:55:46.730Z\"}}], \"cna\": {\"title\": \"Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code\", \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"CBF\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 6.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"LOW\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"LOW\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"NONE\"}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 4.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"LOW\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"repo\": \"https://github.com/pydantic/pydantic-ai\", \"vendor\": \"pydantic\", \"product\": \"pydantic-ai-harness\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"lessThan\": \"0.59.0\", \"versionType\": \"semver\"}], \"packageURL\": \"pkg:pypi/pydantic-ai-harness\", \"defaultStatus\": \"unaffected\"}], \"datePublic\": \"2026-10-15T20:54:31.000Z\", \"references\": [{\"url\": \"https://github.com/pydantic/pydantic-ai/pull/10362\", \"tags\": [\"issue-tracking\", \"patch\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949\", \"tags\": [\"patch\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0\", \"name\": \"pydantic-ai-harness v2.59.0 Release Notes\", \"tags\": [\"release-notes\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://pypi.org/project/pydantic-ai-harness/0.59.0/\", \"tags\": [\"product\"]}, {\"url\": \"https://www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-call-limit-bypass-via-run-code\", \"name\": \"VulnCheck Advisory: Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-770\", \"description\": \"Allocation of Resources Without Limits or Throttling\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-10-21T12:39:43.886Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-114386\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-10-21T19:55:49.371Z\", \"dateReserved\": \"2026-10-21T11:46:40.374Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-10-21T12:39:43.886Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.