GitHub Agentic Workflows Tools Ecosystem
Warn
Audited by Snyk on Mar 4, 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.md explicitly enables fetching and browsing arbitrary public web content (see "🌐 Web Tools" — AI-Powered Web Search and HTTP requests — and "🌐 Playwright Tools" — playwright.browserNavigate), meaning the agent will ingest untrusted third‑party webpages whose content can materially influence subsequent tool use and decisions.
Audit Metadata