uv-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill's documentation shows commands that fetch and execute content from arbitrary public sources (e.g., uv add "git+https://github.com/user/repo", uv add --index , uv pip install --index-url , uvx --from httpie http https://api.example.com, and installer curl | sh), which clearly ingests untrusted, user-provided web content that the agent would read/execute as part of its workflow.