frappe-doctype-builder
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the generation of structured JSON and controller code from user requests, which constitutes an indirect prompt injection surface.
- Ingestion points: User prompts defining DocType fields and properties processed by SKILL.md.
- Boundary markers: The skill does not define delimiters or markers to isolate user-supplied data from generation instructions.
- Capability inventory: Capability to instruct the agent to write file structures (.json, .py, .js) and recommendation of CLI commands such as 'bench migrate'.
- Sanitization: There are no specified procedures for sanitizing or escaping user input before it is embedded into logic fields like 'depends_on' or 'eval:' expressions.
Audit Metadata