slides-grab-design

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly tells the agent to ask the user for a Google/GEMINI API key if the Nano Banana API is unavailable, which would require the LLM to receive and potentially reuse secret API keys (risking verbatim exposure), rather than relying solely on environment-based or CLI-managed auth.

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches/downloads open web content (e.g., "slides-grab fetch-video --url " / "yt-dlp" and fallback "web search + download into /assets/") and permits downloading remote images/videos for use in slides, so it ingests untrusted public third-party content as part of its runtime workflow which could influence design decisions or subsequent actions.