frappe-tweaks-sync-job-expert

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a framework that processes data from Frappe DocTypes through Python controllers, representing an indirect prompt injection surface.
  • Ingestion points: The framework ingests untrusted data via source_doc, a user-provided context dictionary, and triggered_by_doc metadata (documented in references/enqueueing.md).
  • Boundary markers: There is no evidence of boundary markers or instructions to the agent to ignore embedded commands within the processed data.
  • Capability inventory: The framework allows for database writes (target_doc.save()), child job creation, and arbitrary Python execution. "Bypass Mode" specifically enables network operations via libraries like requests (as shown in references/implementation.md).
  • Sanitization: The implementation guide does not mandate or describe specific sanitization techniques for the input data before it is used in logic or written to targets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 08:32 AM
Security Audit — agent-trust-hub — frappe-tweaks-sync-job-expert