ghwf4-review

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Fetch Issue/PR with comments" using gh (gh issue view --json body,comments and gh pr view --json comments,reviews), which causes the agent to ingest user-generated GitHub issue/PR content that it must interpret and that can change review outcomes and follow-up actions (commits, PR updates, labels).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 11:35 PM