simvoly
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: 0.70). This skill's SKILL.md explicitly allows proxying requests to arbitrary Simvoly endpoints via Membrane (see "Proxy requests" /
membrane request CONNECTION_ID /path/to/endpoint) and exposes content types like Website Pages, Blogs, and Form Submissions — untrusted/user-generated third‑party content that the agent would read and could influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata