research
Warn
Audited by Snyk on Mar 5, 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 explicitly instructs the agent to run web searches (via the gemini bash command or fallback WebSearch) and to use the docs-seeker to read GitHub repositories—public, untrusted third-party content that the agent must ingest and act on as part of its research workflow.
Audit Metadata