odoo-report-design
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of Odoo records within QWeb templates, which represents a potential attack surface for indirect prompt injection if record data contains malicious instructions. However, the skill explicitly mitigates this by instructing developers to use escaped output by default and treat rich HTML as a documented trust boundary.
- Ingestion points: Model data processed in
docsloops inREPORT-DESIGN.md. - Boundary markers: Explicit instructions to use
t-outandt-fieldfor escaping. - Capability inventory: File rendering (HTML/PDF) and data iteration via QWeb.
- Sanitization: Warnings against the use of
t-rawfor ordinary user data.
Audit Metadata