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 runtime documentation from https://ai.google.dev/gemini-api/docs/llms.txt (and related https://ai.google.dev/gemini-api/docs/*.md.txt pages) as a fallback source of truth that the agent must read and follow, meaning remote content is fetched at runtime and directly controls agent instructions.