jamroom
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). The skill's workflow explicitly includes actions that fetch user-generated content (e.g., "Get Forum", "Get Blog", "Get RSS Feed", "Get Chat", "Get Social Network") and allows proxying arbitrary Jamroom API requests via Membrane, so the agent will ingest third-party/public user content from Jamroom instances as part of its runtime behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata