dast-workflow
Warn
Audited by Snyk on May 18, 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 instructs running web DAST tools (ZAP, Burp, Nuclei) that crawl and fetch responses from target web applications — including ephemeral preview URLs (Vercel/Heroku) and potentially external hosts if not scoped — meaning the agent will ingest and act on untrusted third‑party web content as part of its workflow (see "Scope and environment", "Scan strategy", and the CI/per-PR examples).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata