external-reference-research
Warn
Audited by Snyk on Feb 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 explicitly performs GitHub code search and broader Web Search (including Stack Overflow and community blogs) and ingests those open/public, user-generated sources as part of its research workflow, exposing the agent to untrusted third-party content.
Audit Metadata