uv

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). This skill instructs the agent to fetch and install packages and metadata from public package indexes (e.g., PyPI) via uv (see troubleshooting.md: "uv fetches package metadata from PyPI or configured indexes") and to run third‑party tools/scripts (uvx, uv run and examples using requests.get), which clearly exposes the agent to untrusted, user-published third-party content and code.