pr
Warn
Audited by Snyk on Feb 27, 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 explicitly instructs the agent to fetch and summarise GitHub issue #$ARGUMENTS using
gh issue view(public, user-generated content) and then use that content to plan and implement code changes and create a PR, so untrusted issue text can materially influence agent behavior.
Audit Metadata