github-tools
Warn
Audited by Snyk on Feb 16, 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). Yes — the skill invokes gh CLI and GraphQL API handlers that fetch GitHub user-generated/public content (e.g., discussion-view, issue-view, pr-view, search-code, run-logs and the raw api endpoint), so the agent will read arbitrary third‑party content that could contain injected instructions.
Audit Metadata