github-modes

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: 0.90). The SKILL.md explicitly instructs the agent to fetch and read user-generated GitHub content (e.g., "gh pr diff", "gh pr view", "gh api repos/:owner/:repo/contents/file.md" and listing issues/PRs) from public repositories, which the skill then uses to drive automated reviews, triage, and merges—exposing it to untrusted third-party content that could inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 03:57 PM