busa-crm
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill manages sensitive CRM data, including contacts, deal pipelines, and interaction histories. It adheres to security best practices by storing this information in a Busabase backend, using environment variables for authentication secrets, and delegating outbound communication to other skills only after explicit human approval.
- [REMOTE_CODE_EXECUTION]: No dangerous remote code execution patterns or arbitrary command execution vulnerabilities were identified. The application uses standard, well-known Node.js dependencies (hono, busabase-sdk) from the skill's official vendor.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external sources such as emails and meeting notes to generate follow-up drafts. It effectively mitigates potential injection risks by implementing a human-in-the-loop review queue where all agent-generated content must be manually approved or revised before being finalized.
Audit Metadata