gemini-api-dev

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching and injecting external documentation at runtime (e.g., https://ai.google.dev/gemini-api/docs/llms.txt and related .md.txt pages) to control agent behavior, so these URLs are runtime dependencies that can alter prompts.