odoo-agency-fleet-review

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from multiple external Odoo instances, creating a potential surface for indirect prompt injection via the content of those databases.
  • Ingestion points: Data is retrieved from Odoo databases using tools such as accounting_health_across_instances, receivable_payable_aging, and search_records (identified in SKILL.md).
  • Boundary markers: The instructions require tagging all output with its source _instance to ensure data provenance, though explicit text delimiters for the processed content are not mandated.
  • Capability inventory: The skill utilizes search and task submission tools that could potentially be influenced by malicious content found within client records.
  • Sanitization: The skill explicitly mentions that field-level ACLs and redacted_fields are enforced by the Odoo environment, providing a structured mechanism for data protection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 03:27 PM
Security Audit — agent-trust-hub — odoo-agency-fleet-review