jlpt-preparation-expert-n5-n1
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional templates without executable code or scripts.
- [PROMPT_INJECTION]: Analysis of the research workflow identifies an indirect prompt injection surface where the agent is instructed to ingest data from external sources.
- Ingestion points: The skill directs the agent to perform web searches and use tools to fetch data from Wikipedia and ArXiv (modules/research-checklist.md).
- Boundary markers: Explicit delimiters or 'ignore embedded instructions' warnings for external data are absent.
- Capability inventory: No subprocess calls, file-write operations, or sensitive network operations were found in the provided files.
- Sanitization: No evidence of input validation or escaping for the ingested research data was found.
Audit Metadata