CVE-2026-114386Medium· 4.8▾ SunlitPydantic 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_n…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 26.4 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
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.
pydantic-ai-harness < 0.59.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-107294Medium· 6.5Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107295High· 7.6Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107293Medium· 5.3Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107292Medium· 6.4Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107291Medium· 4.3Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107290Medium· 6.5Pydantic AI is a Python agent framework for building applications and workflows with Generative AI