learning-knowledge-base-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Category 8: Indirect Prompt Injection] (SAFE): The skill has a data ingestion surface via the 'content' parameter. However, it lacks any exploitable capabilities. * Ingestion points: skill.py (parameters in execute method). * Boundary markers: Not present. * Capability inventory: None; the skill only returns a dictionary and does not interact with the OS or network. * Sanitization: Not present, but unnecessary given the lack of downstream execution risks.
- [General Code Quality] (SAFE): The script references an undefined variable 'skill_dir' in the 'execute' method f-string and artifacts list, which will trigger a NameError at runtime but does not constitute a security vulnerability.
Audit Metadata