researcher

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly specifies HTTP request headers containing API keys/Bearer tokens (e.g., x-api-key: <SCRAPE_CREATORS_API>, Authorization: Bearer <VIDJUTSU_API_KEY>) and shows request templates that the agent is expected to produce, which encourages inserting real secret values verbatim rather than using secure runtime-only mechanisms.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public, user-generated Instagram and TikTok content (e.g., Scrape Creators endpoints like /instagram/post, /instagram/post/comments, /tiktok/video and search calls) and feeds videos to VidJutsu for analysis, and those third‑party contents and derived analyses directly inform the agent's research brief and downstream actions, so untrusted content could influence behavior.