kelly-legal-precedent-desk
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate business workflow for legal precedent research with clear boundaries and human review checkpoints.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or unauthorized data exfiltration patterns were found. The skill correctly uses environment variables and standard OAuth for connecting to the Busabase backend.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution. Dependencies are pinned to specific versions in package.json.
- [COMMAND_EXECUTION]: Local script execution is restricted to the provided utility scripts for data ingestion and export, which are triggered by the user/agent as part of the intended workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for case data, but mitigates risk through a mandatory human review queue and proper HTML escaping in the application UI.
Audit Metadata