liondesk
Warn
Audited by Snyk on Mar 28, 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.md instructs the agent to use Membrane to run actions and proxy arbitrary requests against the Liondesk API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which causes the agent to fetch and interpret third-party, user-generated CRM content that could contain instructions influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata