helpcrunch
Warn
Audited by Snyk on Apr 23, 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 explicitly fetches user-generated content from HelpCrunch (e.g., "Get Chat Messages", "Search Chats", "HelpCrunch Article" and via the Membrane proxy/request to the HelpCrunch API) which the agent is expected to read and act on (create-message, update-chat, etc.), creating a clear avenue for untrusted third-party content to influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata