connect-ai-odoo
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for querying and processing Odoo data, which creates a surface for indirect prompt injection if retrieved records contain malicious instructions.
- Ingestion points: Data returned from SQL queries on tables like
res_partnerand output from theCallProcedureRPC escape hatch (SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to treat data from the Odoo connection as untrusted.
- Capability inventory: The skill enables the agent to perform SQL operations (SELECT, INSERT, UPDATE) and execute arbitrary Odoo model methods through
CallProcedure(SKILL.md). - Sanitization: No data sanitization or validation logic is defined to filter malicious payloads that might be stored within Odoo fields.
Audit Metadata