audit-hermes-agent-skills
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses subprocess.run to execute the hermes CLI tool and a helper script within the local environment's Python interpreter to retrieve system-level information. These operations are restricted to the local environment and are necessary for the skill's primary purpose.
- [DATA_EXPOSURE]: The skill reads from local configuration files (config.yaml) and an internal SQLite database (state.db) to extract usage statistics. This data is processed locally to generate a user report and is not transmitted over the network.
- [EXTERNAL_DOWNLOADS]: No external downloads or network requests are performed by the skill. All operations are local.
Audit Metadata