n2-free-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). This is a GitHub repository hosted under an unrecognized user (spooky-may) containing a third‑party "skill" that would be installed/executed via npx/clawhub (which runs remote code), is not from an official vendor, and appears unvetted — making it potentially suspicious.

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

• Third-party content exposure detected (high risk: 0.85). This skill performs free web search at runtime (via SearXNG) and will ingest fetched public web page text into the agent’s LLM context, which is outsider-authored free-form content.