validate-pr

Warn

Audited by Snyk on Feb 27, 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 explicitly fetches and reads GitHub PR bodies using "gh pr view --json title,body,headRefName" (user-generated content from a public third-party) and uses that content to decide checks and to construct follow-up commands (e.g., a gh pr edit that embeds the PR body), so untrusted third-party text can materially influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:47 PM