find-skills

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow ingests only first-party search results metadata via search_skills(query) and installs a specific third-party skill only after explicit user install intent (install_skill(install_source)), but it does not read arbitrary outsider-authored free text without actively selecting/fetching a specific item.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill shows a runtime call to install_skill("claude-plugins:vercel-labs/agent-skills/skills/react-best-practices") (SKILL.md:109) which will fetch and install third‑party code that runs with full agent permissions, so external content is retrieved at runtime and can execute.