erpnext-impl-serverscripts

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on secure development practices for the Frappe/ERPNext framework. It provides implementation workflows that include mandatory permission checks and validation logic.
  • [SAFE]: The 'Anti-Patterns' reference in references/anti-patterns.md provides high-quality security guidance, educating users on how to avoid SQL injection via parameterized queries, prevent sandbox escapes, and avoid the N+1 query problem.
  • [PROMPT_INJECTION]: The skill templates establish an ingestion surface for external data through the implementation of custom API endpoints.
  • Ingestion points: Untrusted user data is captured via frappe.form_dict in SKILL.md (Workflow 4) and references/examples.md (Example 6).
  • Boundary markers: While explicit text delimiters are not used, the templates implement logical validation and permission checks (frappe.has_permission) to manage data flow.
  • Capability inventory: The provided patterns have the capability to perform database operations via frappe.db, manage system documents via frappe.get_doc, and send communications via frappe.sendmail.
  • Sanitization: Robust sanitization and validation are standard throughout the skill, including the use of frappe.db.escape, parameterized SQL queries, and input type casting (e.g., cint).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 05:38 PM