slides-grab-design

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly tells the agent to ask the user for GOOGLE_API_KEY (or GEMINI_API_KEY) when those keys are unavailable for the Nano Banana API, which requires the agent to accept and potentially include secret API keys in generated workflows/commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch and download open web content (e.g., "slides-grab fetch-video --url " in Workflow step 10 and the Rules note to "fall back to web search + download into /assets/" if image-generation APIs fail), so it will ingest untrusted, user-generated third‑party content at runtime and incorporate it into slides.