agencyzoom
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill follows standard practices for integrating third-party services using a command-line interface.\n- [COMMAND_EXECUTION]: The instructions utilize the ClawLink CLI tool (@useclawlink/cli) to execute authorized actions within the AgencyZoom environment.\n- [EXTERNAL_DOWNLOADS]: The skill relies on the @useclawlink/cli Node.js package. This package is managed by the vendor, clawlink-hq, and is retrieved from the standard NPM registry.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from the AgencyZoom API.\n
- Ingestion points: Data returned from AgencyZoom actions and descriptions processed by the agent.\n
- Boundary markers: The instructions explicitly advise the agent to confirm with the user before performing any write operations.\n
- Capability inventory: Execution of CRM actions (create, delete, update) via the CLI tool.\n
- Sanitization: Relies on CLI input validation and agent-level safety protocols.
Audit Metadata