uv-find-skills

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly directs using "npx skills find [query]" and links to https://skills.sh and installing packages from GitHub/other sources, so the agent is expected to fetch and interpret public, user-contributed skill metadata and packages (untrusted third-party content) that can change what the agent installs and does.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime installation via npx skills (e.g., npx skills add vercel-labs/agent-skills@vercel-react-best-practices and links like https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices), which fetches and installs remote skill code that can directly control agent prompts or execute code.