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, and git commit for navigating the file system and managing repository changes.
  • [SAFE]: The skill references internal management scripts located in ~/.hermes/scripts/, such as regen_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
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:55 AM
Security Audit — agent-trust-hub — hermes-agent-skill-authoring