find-skills

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only covers searching for and recommending skills via npx skills find / browsing at skills.sh, with no indication it scrapes or LLM-ingests arbitrary outsider-authored free text unless the user elects to install a specific skill, and even then it instructs to read installed instructions before acceptance.

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

• Potentially malicious external URL detected (high risk: 0.80). The document instructs running "npx skills add vercel-labs/agent-skills@react-best-practices" (and the generic "npx skills add owner/repo@skill") which at install time fetches remote skill code/instructions that "your agent will follow", meaning fetched external content can directly control agent prompts or execute code.