cloudlayer
Warn
Audited by Snyk on Apr 25, 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). This skill explicitly integrates Cloudlayer—which "captures website screenshots, converts web pages to PDFs, and extracts website content"—and lists actions like "URL to Image" and "URL to PDF" that fetch arbitrary webpage URLs, so the agent will ingest and potentially act on untrusted third‑party web content (see SKILL.md "Cloudlayer" overview and "Popular actions").
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata