nushell-usage

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The file references/advanced-patterns.md contains multiple examples of network operations using the built-in http get command and the curl utility to fetch data from URLs. \n- [COMMAND_EXECUTION] (LOW): Documentation in references/advanced-patterns.md demonstrates the execution of external system commands, specifically curl, to handle network failures in a 'robust-fetch' pattern. \n- [Indirect Prompt Injection] (LOW): The skill documents patterns for ingesting untrusted data from external sources (URLs) and processing it through functions like from json. This represents an attack surface for indirect prompt injection. \n
  • Ingestion points: http get $url and curl -s $url patterns in references/advanced-patterns.md. \n
  • Boundary markers: None present in the code examples. \n
  • Capability inventory: Network access (http get, curl), file system writing (save-to-file), and parallel execution (par-each). \n
  • Sanitization: No explicit sanitization or input validation logic is shown in the provided examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:02 PM