hiram-backend
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to organize its output by creating directories via shell commands. It mitigates potential argument injection by directing the agent to convert user-provided input into URL-safe strings.
- [SAFE]: The skill's primary functions, involving reading project source code for auditing and writing reports to specific local directories, are transparently documented and consistent with its role as a consulting subagent.
Audit Metadata