freshlearn
Warn
Audited by Snyk on Apr 24, 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 describes calling Freshlearn via Membrane (e.g., the "Popular actions" like list-members/list-completed-courses and the "Proxy requests" command
membrane request CONNECTION_ID /path/to/endpoint), which ingests third‑party/user‑generated Freshlearn content that the agent reads and can influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata