The Agent Skills Directory

[SAFE]: The skill serves as an educational resource for Frappe database operations, emphasizing security best practices and official framework methodologies.
[COMMAND_EXECUTION]: The skill documents methods like frappe.db.sql and frappe.qb.run() for executing database queries. It provides mandatory instructions to use parameterized queries to prevent SQL injection vulnerabilities and highlights vulnerable patterns as anti-patterns to avoid.
[DATA_EXFILTRATION]: The skill describes methods for reading data from the database (e.g., frappe.get_all, frappe.db.get_list). While it documents patterns for bypassing permission checks for system-level operations (ignore_permissions=True), these are standard framework features documented for legitimate development use cases with no evidence of malicious exfiltration intent.
[PROMPT_INJECTION]: No malicious instructions, behavioral overrides, or safety bypass patterns were detected in the skill metadata or reference files.

frappe-core-database