skills/openaec-foundation/erpnext_anthropic_claude_development_skill_package/erpnext-impl-scheduler/Gen Agent Trust Hub
erpnext-impl-scheduler
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [SAFE]: The skill serves as an educational resource for developers, providing production-ready code examples and clear documentation on best practices within the Frappe ecosystem.
- [COMMAND_EXECUTION]: The documentation references standard administrative CLI commands (e.g., bench migrate and bench scheduler status) which are essential for registering and monitoring background tasks in the target environment.
- [DATA_EXFILTRATION]: Analysis confirms that no sensitive data is transmitted to unauthorized destinations. Code examples for external API synchronization correctly demonstrate the use of system-managed configuration for secret storage rather than hardcoding credentials.
- [PROMPT_INJECTION]: The skill identifies surfaces for indirect prompt injection through bulk data processing implementation patterns (e.g., CSV imports in Example 3). 1. Ingestion point: file_url in myapp/importer.py. 2. Boundary markers: None present in the code examples. 3. Capability inventory: Database write access (doc.insert) and notification publishing (frappe.publish_realtime). 4. Sanitization: The implementation relies on standard library modules (csv) and is necessary for the skill's functional purpose.
Audit Metadata