npj-computational-materials
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of domain-specific instructions for evaluating academic manuscript fit for a specific journal. No malicious patterns such as prompt injection, obfuscation, or unauthorized network access were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest internal resource files (../../resources/source-basis.md and ../../resources/official-source-map.md) to establish a context for official guidelines. These ingestion points are restricted to local paths and are used to ensure the agent uses authoritative sources for its advice, which is a standard accuracy practice.
Audit Metadata