nooks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill tells the agent to read a stored Google Places API key from kyp/nooks/nooksconfig.yml and to include it verbatim in API request headers (X-Goog-Api-Key) / example requests, which requires the LLM to handle and emit secret values.

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md workflow explicitly instructs the agent to "Search the web (name + city/area)" and to call the Google Places API (places.googleapis.com) and fetch Maps/image links (maps.app.goo.gl / image search) to pre-fill place metadata, so it ingests untrusted public third‑party content that can influence how the agent fills fields and acts.