odoo-website
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle web traffic and portal data, creating a surface for indirect prompt injection where instructions could be embedded in external data processed by the agent.
- Ingestion points: The skill provides patterns for Odoo controllers that accept user-provided arguments (e.g.,
**kwargsinWEBSITE-PATTERNS.md) and process record IDs. - Boundary markers: The instructions explicitly warn to "Treat every public or portal parameter as untrusted" and to "validate record ownership" (SKILL.md).
- Capability inventory: The provided code examples use standard Odoo ORM methods (
search,browse,render) and do not perform high-risk operations like file writing, network calls to untrusted domains, or arbitrary code execution across all scripts. - Sanitization: The skill mandates using
t-outfor escaping user data in templates and emphasizes input normalization and validation before ORM calls (QWEB-PATTERNS.md, WEBSITE-PATTERNS.md).
Audit Metadata