review

Warn

Audited by Snyk on Apr 6, 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.md explicitly instructs the agent to run "gh pr view / gh pr diff" and to read PR title/body, commits and diffs from GitHub (public, user-generated content) in Step 1–2 to determine intent and drive review actions, so untrusted third‑party content is ingested and can materially influence decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 6, 2026, 01:29 PM
Issues
1