wiki-ingestion

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents how to use a specific CLI tool (hermes) for wiki management. All operations described—such as file snapshots, article classification, and batch ingestion—are standard data management tasks.
  • [COMMAND_EXECUTION]: The skill includes examples of commands like hermes wiki ingest and hermes wiki monitor. These are documented as part of the intended functionality for managing the wiki and do not represent unauthorized or malicious command execution.
  • [EXTERNAL_DOWNLOADS]: The ingestion process supports fetching content from URLs. This is a core feature of the tool for ingesting research material and follows standard behavior without evidence of malicious exfiltration or remote code execution.
  • [REMOTE_CODE_EXECUTION]: While the skill mentions writing custom classifiers in Python (plugins/classifiers/<name>.py), it emphasizes that these must be explicitly trusted via hermes wiki plugins trust, which is a security best practice to prevent the execution of untrusted code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 03:01 AM
Security Audit — agent-trust-hub — wiki-ingestion