command-development
Warn
Audited by Snyk on May 10, 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.md "PR #$1 Workflow" explicitly runs a remote fetch (!
gh pr view $1) to load a GitHub pull request (public, user-generated content) which the agent is expected to read and act on (review/approve), creating a clear vector for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata