validate

Warn

Audited by Snyk on May 12, 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). This skill explicitly fetches and ingests user-generated PR diffs via "gh pr diff " as part of its /validate --mode=pr workflow (Step 2), meaning it reads untrusted, third-party GitHub content that can directly influence judge decisions and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 10:58 AM
Issues
1
Security Audit — snyk — validate