odoo-web-security
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 ingest and analyze user-provided Odoo code, routes, and templates for security vulnerabilities. This creates a potential surface for indirect prompt injection where malicious instructions hidden in the code being reviewed could attempt to influence the agent's output.
- Ingestion points: The skill instructs the agent to review Odoo website code, public controllers, JSON routes, and QWeb assets provided in the session context (referenced in SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to separate the code being analyzed from the agent's primary instructions.
- Capability inventory: The skill frontmatter does not request access to any dangerous tools such as shell execution, network access, or file system writing.
- Sanitization: The skill does not implement or require specific sanitization or escaping of the input data before processing.
Audit Metadata