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
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 04:47 PM