refining

Warn

Audited by Snyk on Mar 4, 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's "Review" workflow explicitly says to "Identify target: PR URL, branch, or current changes" (SKILL.md, "Review" section), which requires fetching and interpreting PR/MR content from external GitHub/GitLab URLs (user-generated, public third‑party content) that can influence review decisions and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 11:29 PM