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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 24, 2026, 10:47 AM
Issues
1