ghm-sot-builder
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and focused on project documentation management. It defines structured templates and quality gates for maintaining consistency in 'Source of Truth' files without introducing any technical risks.- [COMMAND_EXECUTION]: The skill uses allowed tools (Read, Write, Edit, Glob, Grep) for their intended purposes of interacting with local markdown documentation. There is no evidence of arbitrary command execution, shell injection, or privilege escalation.- [DATA_EXFILTRATION]: No network-related commands or exfiltration patterns were found. The skill does not access sensitive credentials, environment variables, or private user data.- [PROMPT_INJECTION]: The skill contains clear procedural instructions that follow standard AI agent guidelines. It does not attempt to override safety filters, extract system prompts, or use deceptive language to manipulate agent behavior.
Audit Metadata