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 instructs the agent at runtime to fetch official docs from https://ai.google.dev/gemini-api/docs/llms.txt (and related ai.google.dev .md.txt pages) as a fallback and use their contents to guide behavior, so these external URLs can directly control the agent's prompts/instructions during execution.