gemini-interactions-api

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching and using external documentation at runtime (e.g., https://ai.google.dev/gemini-api/docs/interactions.md.txt), which the agent must retrieve before writing code and thus external content directly controls prompts/instructions and is a required dependency.