triage-pr-reviews

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests user-generated GitHub PR review comments via the "gh pr-reviews ... --json" (and related "gh pr view") steps, and the agent is required to read and act on those comment bodies to classify and recommend actions, so untrusted third-party content can materially influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 09:31 AM