pr-review

Warn

Audited by Snyk on Mar 17, 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 workflow explicitly calls gh pr view / gh pr diff to fetch PR title/body and comments (SKILL.md Step 2) and reads PR diffs and comments — user-generated GitHub content — which the agent ingests and uses to drive review decisions, exposing it to untrusted third-party input.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 17, 2026, 11:42 AM
Issues
1