learning-tutor-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Indirect Prompt Injection (INFO): The skill processes untrusted external content via the 'content' parameter. Evidence Chain: 1. Ingestion point: 'content' parameter in 'skill.py'. 2. Boundary markers: Absent. 3. Capability inventory: No command execution, file system writing, or network operations detected in 'skill.py'. 4. Sanitization: Absent. Risk Level: INFO; the skill only handles data for display/processing without dangerous side effects.
- General Code Quality (INFO): The 'execute' method in 'skill.py' attempts to use a variable named 'skill_dir' which is not defined in the scope. This is a runtime bug rather than a security vulnerability.
Audit Metadata