ontology
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill includes a robust path validation mechanism in
scripts/ontology.pythat prevents directory traversal by ensuring all file access is restricted to the workspace root. - [SAFE]: Secure deserialization is practiced through the use of
yaml.safe_load, protecting the environment from arbitrary code execution via malicious schema files. - [COMMAND_EXECUTION]: Local management of the knowledge graph is performed via a CLI script (
scripts/ontology.py). Property data is safely parsed as JSON, mitigating injection risks during command invocation. - [SAFE]: The skill documentation and validation code enforce a 'no-secrets' policy by specifically flagging and blocking the inclusion of raw credentials (like passwords or tokens) in the graph entities.
Audit Metadata