learning-discussion-designer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [General Analysis] (SAFE): No malicious patterns detected. The script handles data structures for educational design and does not perform network or file system operations.
- [Indirect Prompt Injection] (LOW): The skill processes user-controlled inputs 'topic' and 'educational_level'. While these are interpolated into the output, the skill lacks capabilities such as network access or shell execution, neutralizing the risk of exploitation. Evidence: 1. Ingestion points: 'topic' and 'educational_level' parameters in skill.py. 2. Boundary markers: None. 3. Capability inventory: No dangerous calls found. 4. Sanitization: Basic string replacement for space characters.
- [Code Quality] (SAFE): The variable 'skill_dir' is undefined in skill.py, which would trigger a NameError at runtime but is not a security risk.
Audit Metadata