CVE-2026-114386: Pydantic AI Harness tool-call limit bypass in nested CodeMode calls
Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.toolcallslimit on nested tool calls dispatched from runcode in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via runnestedcall() without checkbeforetoolcall, exceeding operator limits on costly or side-effecting tools.
Published Oct 21, 2026 · Updated Oct 23, 2026
Affected packages
pydantic-ai-harness
- Ecosystem
- PyPI
- Affected
- < 0.59.0
- Fixed in
- 0.59.0
- Check
pip show pydantic-ai-harness
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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
- https://nvd.nist.gov/vuln/detail/CVE-2026-114386
- https://github.com/pydantic/pydantic-ai/pull/10362
- https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949
- 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/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
- https://github.com/advisories/GHSA-3589-pxp7-3gj8
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
