github-agentic-workflows
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: 0.80). The skill explicitly includes a Web MCP Server / web-fetch tool (Tool Configuration and MCP Architecture) and CLI commands like "gh aw add " which let the agent fetch and ingest arbitrary public web pages/URLs, meaning it will read untrusted third‑party/user‑generated content that can influence its decisions and subsequent tool actions.
Audit Metadata