devops
Warn
Audited by Snyk on Apr 10, 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 includes runtime headless-browser workflows (references/browser-rendering.md and references/cloudflare-workers-advanced.md) that navigate to arbitrary third-party URLs (e.g., page.goto(message.body.url) and page.goto('https://news.ycombinator.com')) and then pass the fetched HTML to an AI extractor (Ai.run), which clearly ingests untrusted, user-generated web content that can influence subsequent tool use and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs users to fetch and run remote installer scripts (e.g., curl https://sdk.cloud.google.com | bash and the Google Cloud SDK tarballs at https://dl.google.com/dl/cloudsdk/... which are presented as installation steps run at runtime), which execute remote code and are required dependencies for the GCP deployment workflows described.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata