Tracing Knowledge Lineages
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's Search Strategies explicitly direct the agent to inspect user-generated, potentially public sources—e.g., "Issue/PR discussions (GitHub/GitLab issue history)" and conversation history—which the agent would read and use to influence decisions, exposing it to untrusted third‑party content.
Audit Metadata