odoo-edi-connector
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for parsing external EDI transaction sets (such as X12 850) and mapping them to Odoo business objects. This creates an indirect prompt injection surface where data from external trading partners could potentially influence the agent's operations.
- Ingestion points: The skill ingests untrusted data through the
edi_file_pathprocessed in theprocess_850function outline inSKILL.md. - Boundary markers: The instructions do not define or mandate the use of explicit boundary markers or delimiters to isolate processed EDI data from the agent's instruction context.
- Capability inventory: The skill is designed to perform write operations in the Odoo database, including the creation of
sale.order,account.move, andstock.pickingrecords. - Sanitization: While the skill advises on deduplication and identifier resolution, it lacks specific guidance on sanitizing the data content to prevent it from being interpreted as instructions by the LLM during the mapping process.
Audit Metadata