gemini-api-dev

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to create custom agents with repositories loaded from external GitHub URLs (e.g., https://github.com/my-org/backend), which exposes the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external MCP server URL (https://gemini-api-docs-mcp.dev) for operational dependency instructions, which constitutes an unofficial external operational dependency.