gh-aw-workflow-authoring
Warn
Audited by Snyk on Mar 12, 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's "Dependency Update Review" workflow example in SKILL.md explicitly lists tools: web-fetch and instructs the agent to check public sources (npm audit, GitHub advisory database, Snyk or similar) — i.e., fetching and interpreting untrusted public web content that directly influences merge/security recommendations and subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The workflow's compile job installs and runs a remote npm package ("npm install -g @github/agentic-workflows-compiler" — https://www.npmjs.com/package/@github/agentic-workflows-compiler) and pulls the actions/checkout@v4 action (https://github.com/actions/checkout), both of which fetch and execute remote code at runtime and are required for the compilation step.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata