workflows
Warn
Audited by Snyk on Feb 16, 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 explicitly opens and ingests arbitrary web pages (browser-pdf-generation: "targetUrl=") and automates dashboard/site scraping (browser-mediavine-csv.md) and spawns agents to research competitors including "user reviews summary" (parallel-research.md), which means it will read untrusted, user-generated public content that could contain indirect prompt injection.
Audit Metadata