vext
Warn
Audited by Snyk on Apr 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly allows issuing proxied requests to arbitrary Vext API endpoints via "membrane request CONNECTION_ID /path/to/endpoint", which will fetch and ingest third‑party (potentially user-generated/untrusted) content that the agent is expected to read and act on, creating an avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata