ghwf1-kickoff

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: 0.90). This skill explicitly fetches GitHub issue and PR content (see "Fetch Issue" step: gh issue view --json title,body,labels,author,comments, and the Revise Processing steps: gh pr view --json reviews,comments and gh issue view --json body,comments), which are untrusted, user-generated third-party inputs that the agent reads and uses to update kickoff docs and drive actions, so they could carry indirect prompt-injection instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 11:35 PM