ontology
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes a secure environment for knowledge management using local structured data files.
- [CREDENTIALS_UNSAFE]: The system design explicitly prevents the storage of sensitive secrets like passwords or API keys by enforcing a schema that requires indirect secret references (secret_ref).
- [DATA_EXFILTRATION]: All data operations are confined to the local 'memory/ontology/' directory. There are no network calls or patterns indicating unauthorized data access.
- [PROMPT_INJECTION]: Triggers and descriptions are strictly related to entity management and knowledge graph operations, containing no safety bypass instructions.
- [COMMAND_EXECUTION]: Python scripts are used for data processing and do not involve the execution of shell commands or the evaluation of untrusted strings.
Audit Metadata