avochato
Warn
Audited by Snyk on Mar 4, 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 and processes user-generated content from Avochato (e.g., the "Popular actions" list includes "Search Messages", "Get Message", "List Messages" and the docs show using "membrane request CONNECTION_ID /path/to/endpoint"), so the agent will read and act on untrusted third-party messages that could contain injected instructions.
Audit Metadata