Vulnerability 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 Score
MEDIUM
Related Weaknesses (CWE)
References
- https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pyd
- https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a
- 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-
FAQ
What is CVE-2026-114386?
CVE-2026-114386 is a vulnerability with a CVSS score of 4.8 (MEDIUM). 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 san...
How severe is CVE-2026-114386?
CVE-2026-114386 has been rated MEDIUM with a CVSS base score of 4.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-114386?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.