cross-agent-skill-audit
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a comprehensive suite of shell commands such as find, grep, test, mv, ln, rm, and git to inspect the local filesystem, verify the existence and integrity of symlinks, and perform maintenance tasks. These commands are integral to the skill's function of synchronizing skill directories between various AI agent platforms.
- [COMMAND_EXECUTION]: The skill references and triggers local workspace scripts, including scripts/_core/sync-agent-configs.sh and scripts/hermes/backfill-skills-to-repo.sh. These are used to automate the synchronization of agent configurations and the migration of skills between repositories.
- [SAFE]: The skill reads the ~/.hermes/config.yaml file to audit the external_dirs configuration. This is a standard administrative operation for the Hermes agent environment and is documented as a core part of the audit procedure to ensure all skill paths are properly registered.
Audit Metadata