odoo-edi-connector

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices for credential management by retrieving Odoo connection details (URL, DB name, API Key) from environment variables using os.getenv rather than hardcoding sensitive values.
  • [SAFE]: The Python examples utilize standard libraries, such as the pyx12 package for X12 parsing and the built-in xmlrpc.client for communicating with the Odoo server.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external EDI files, which is an inherent attack surface for document processing skills. The implementation includes basic validation checks, such as verifying the existence of partners and products in Odoo before generating new records.
  • Ingestion points: edi_file_path used in the process_850 function within SKILL.md.
  • Boundary markers: None explicitly defined; the skill relies on the structure of the X12 format.
  • Capability inventory: The skill has the capability to search for and create records in an Odoo instance via the XML-RPC API.
  • Sanitization: The code performs lookups for existing Odoo objects but does not explicitly sanitize the string content of individual EDI segments before interpolation into API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:49 AM
Security Audit — agent-trust-hub — odoo-edi-connector