ac-knowledge-graph
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious behavior detected. The skill's primary function is managing internal project knowledge via a local JSON file.
- Indirect Prompt Injection (SAFE): The skill possesses a data ingestion surface but the risk is negligible. 1. Ingestion points: _load_graph in scripts/knowledge_graph.py reads data from .claude/knowledge-graph.json. 2. Boundary markers: None. 3. Capability inventory: Limited to internal state management and JSON file persistence in the project directory. 4. Sanitization: Uses Python's json module and dataclass instantiation for basic structural validation.
Audit Metadata