gemini-api

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves searching and fetching content from arbitrary web pages via search grounding or URL context tools (references/structured_and_tools.md), 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 (high risk: 0.70). The skill contains an operational dependency on an unverified third-party NPM package hosted via npx in references/advanced_features.md, making it a weak/unknown external runtime dependency.