CVE-2026-114386
4.8 MEDIUMpublic exploit availablePublished 2026-10-21 · Updated 2026-10-22
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD description
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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
Weaknesses
CWE-770
Public exploit & PoC references
- https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680
- https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949
- https://github.com/pydantic/pydantic-ai/pull/10362
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0
All references
- https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680
- https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949
- https://github.com/pydantic/pydantic-ai/pull/10362
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0
- https://pypi.org/project/pydantic-ai-harness/0.59.0/
- https://www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-call-limit-bypass-via-run-code
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2023-54404PoC
- MEDIUMCVE-2025-12767
- MEDIUMCVE-2025-36061
- UNSCOREDCVE-2025-8352
- MEDIUMCVE-2026-100274
- MEDIUMCVE-2026-100350PoC
- MEDIUMCVE-2026-100508
- MEDIUMCVE-2026-100600PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.