erpnext-code-interpreter

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): The content is purely instructional for ERPNext logic and does not contain any attempts to bypass safety guardrails.
  • [Data Exposure] (SAFE): No hardcoded secrets, sensitive file paths, or network exfiltration patterns were identified.
  • [Remote Code Execution] (SAFE): The skill provides logic for identifying when scripts are needed but does not perform any remote code downloads or execution itself.
  • [Indirect Prompt Injection] (LOW): The skill facilitates the processing of untrusted user input to generate ERPNext logic. While it defines clear mapping logic, it lacks explicit boundary markers or sanitization steps for that input, though this is typical for a development reference guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:05 PM