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.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
pydantic pydantic-ai-harness
Default version status: unaffected
0 to < 0.59.0affected
pkg:pypi/pydantic-ai-harnessReferences
- https://github.com/pydantic/pydantic-ai/pull/10362 ↗
- https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949 ↗
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0 ↗
- https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680 ↗
- 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 ↗