one-rollout-every-department

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the user to install the Clueso MCP tool using standard shell commands such as 'claude mcp add'. This is a legitimate setup process for the required platform integration.
  • [EXTERNAL_DOWNLOADS]: References to external domains like 'connect.clueso.io' and 'help.clueso.io' are for vendor-provided services and documentation, which are safe in the context of this skill.
  • [PROMPT_INJECTION]: The skill analyzes transcriptions of user recordings, which is an indirect prompt injection surface. However, the workflow mitigates this through mandatory verification and review steps before final output generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — one-rollout-every-department