init-or-refactor-agents-md
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is designed for local documentation management and includes human-in-the-loop confirmation steps.
- [PROMPT_INJECTION]: No evidence of prompt injection, bypass attempts, or instructions to ignore safety guidelines. On the contrary, the skill explicitly instructs the agent to never simplify away security or trust-boundary validation.
- [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were found. The skill only reads and writes repository-local files.
- [EXTERNAL_DOWNLOADS]: No external dependencies, scripts, or remote code are downloaded or executed.
- [COMMAND_EXECUTION]: While the skill mentions project commands in the documentation it generates, it does not instruct the agent to execute arbitrary shell commands itself.
Audit Metadata