find-tool

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow explicitly directs the agent to “Search current authoritative sources” and to read external ecosystem sources (e.g., npm/PyPI/Homebrew/GitHub/web pages) and incorporate their content into the LLM for comparison, which is outsider-authored free text fetched at runtime.