review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill is composed entirely of markdown instructions. There are no associated scripts or executable files provided or referenced for execution.
- [Data Exposure] (SAFE): The skill accesses a local data file to personalize its response. Evidence: Reference to 'data/learner-profile.json' in the skill steps. Assessment: This is part of the intended primary purpose and no network tools exist to leak this data.
- [Indirect Prompt Injection] (SAFE): Potential for data ingestion from external files. 1. Ingestion points: 'data/learner-profile.json' in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (only text generation). 4. Sanitization: Absent. Assessment: The risk is negligible as the agent has no dangerous capabilities to exploit through injected content.
Audit Metadata