hermes-agent-skill-authoring
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation and YAML frontmatter. It provides instructions on how to format other skills but does not include scripts, tools, or executable commands that run in the agent's environment.
- [SAFE]: All instructions follow standard development practices for the platform. The provided Python snippet for validation is a benign example meant for local testing by the user and does not interact with external networks or sensitive files.
- [METADATA_POISONING]: The metadata fields (name, description, author, version) are consistent with the content of the skill and do not contain deceptive instructions or injection patterns.
Audit Metadata