backend-study
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of text-based instructions for a Socratic tutoring persona. No commands, file operations, or network requests are present.
- [Indirect Prompt Injection] (SAFE): Although the skill processes user-provided topics and answers, it lacks any dangerous capabilities (e.g., shell access, file writing, or network transmission) that could be exploited. 1. Ingestion points: User input via text responses and topic selection. 2. Boundary markers: Not explicitly defined in instructions. 3. Capability inventory: Uses the
AskUserQuestiontool for UI selection; no system or network tools. 4. Sanitization: Not explicitly defined.
Audit Metadata