watch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to AskUserQuestion for Groq/OpenAI API keys and then write lines like GROQ_API_KEY=... or OPENAI_API_KEY=... into ~/.config/watch/.env, which requires the LLM to accept and embed secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.85). Yes: the required runtime path downloads/reads outsider-authored captions/transcripts from a user-supplied URL (yt-dlp VTT files) and then prints the resulting free-text transcript into the LLM context via scripts/watch.py (Step 3/4: parse_vtt → format_transcript → stdout transcript block).