many_chat-automation
Warn
Audited by Snyk on Feb 16, 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 explicitly performs ManyChat operations (chatbot flows, subscribers, broadcasts, and messenger automation) via the ManyChat toolkit and RUBE_MULTI_EXECUTE_TOOL/RUBE_SEARCH_TOOLS, which requires fetching and reading user-generated subscriber/messages and flow content from a third-party service (ManyChat), exposing the agent to untrusted third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the external MCP server at https://rube.app/mcp at runtime, and that server provides tool schemas/recommendations and executes RUBE_* tool calls which directly control agent instructions and perform remote execution.
Audit Metadata