zenrows
Warn
Audited by Snyk on Apr 21, 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.md explicitly documents using ZenRows to scrape public websites (e.g., "Scrape" actions) and instructs using Membrane's proxy request (membrane request CONNECTION_ID /path/to/endpoint) to fetch arbitrary web content, meaning the agent will ingest untrusted third‑party pages that could contain instructions affecting its behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata