uv-advanced

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

• Third-party content exposure detected (high risk: 0.90). The skill’s documentation and examples show uv fetching and executing content from public, user-controlled sources—e.g., installing packages and git deps from PyPI and GitHub (uv pip install git+https://github.com/...), configuring indexes pointing to pypi.org or arbitrary URLs ([[tool.uv.index]] url = "https://pypi.org/simple"), and running ephemeral tools/HTTP requests (uvx httpie GET https://api.github.com or script examples that call external APIs)—which means the agent may ingest and act on untrusted, third-party content.