gemini-system
Warn
Audited by Snyk on Mar 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md and references/lib-research-task.md) explicitly instructs Gemini to use Google Search and fetch public web sources (official docs, GitHub READMEs/issues/discussions, Stack Overflow, blog posts, arbitrary URLs) and to ingest and save those findings for downstream use (e.g., documentation and Codex), so untrusted, user-generated content can be read and materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata