changelog
Warn
Audited by Snyk on Feb 17, 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). This skill ingests user-generated, public GitHub content via commands like "gh pr list --state merged ... --json number,title,body,labels" and "gh issue list ... --json number,title,body,labels", so the agent will read untrusted third-party PR/issue text as part of its workflow.
Audit Metadata