gemini-cli
Warn
Audited by Snyk on Jun 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime path includes the
google_web_searchtool (and potentiallyweb_fetch) which fetches public web pages and injects their scraped/free-form text into the agent’s LLM context for summarization/grounding.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata