hermes-agent-skill-authoring
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard system commands such as
ls,git add, andgit commitfor navigating the file system and managing repository changes. - [SAFE]: The skill references internal management scripts located in
~/.hermes/scripts/, such asregen_skill_directory.py. These are part of the agent's expected execution environment for self-maintenance and do not involve untrusted remote sources. - [SAFE]: The included Python validation snippet uses
yaml.safe_load(), adhering to security best practices for handling YAML data. - [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized network activity was detected. The content is purely instructional for internal development workflows.
Audit Metadata