review-pr

Warn

Audited by Snyk on Apr 19, 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). The skill explicitly fetches and ingests user-generated PR content from GitHub (e.g., Phase 1 commands gh pr view $PR_NUMBER / gh pr diff $PR_NUMBER and the captured CHANGED_FILES), and passes that untrusted PR/diff content into agent prompts and orchestration (agents use ${CHANGED_FILES} and PR metadata to decide actions and verdicts), so third-party PR content can materially influence tool use and agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 19, 2026, 02:03 AM
Issues
1