nu-shell
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill is a documentation guide with no executable components or referenced external scripts.
- [COMMAND_EXECUTION] (SAFE): Examples describe Nushell syntax for processing tabular data. These are legitimate usage patterns for a shell and are not malicious.
- [DATA_EXFILTRATION] (SAFE): The skill demonstrates reading and writing common data formats (JSON, CSV). No access to sensitive files (e.g., SSH keys) or network exfiltration patterns were detected.
- [PROMPT_INJECTION] (SAFE): The skill describes tools that ingest external data, creating an indirect prompt injection surface. Evidence: 1. Ingestion points: 'open' command in SKILL.md. 2. Boundary markers: Absent in documentation examples. 3. Capability inventory: File system read/write and script execution via Nushell. 4. Sanitization: Not addressed in the guide.
Audit Metadata