odoo-grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the local codebase (manifests, models, security files) to gather context for its design review. While reading external files is an entry point for indirect prompt injection, this is a standard and necessary function for a code review tool. No dangerous capabilities are triggered by the ingested data.
- [DATA_EXPOSURE]: The instructions reference environment variables such as
$ODOO_SOURCEand$ODOO_BASE_COMMANDto locate the project and project-specific documentation. This is a common pattern for development tools to integrate with a user's local environment and does not involve exfiltration of sensitive information.
Audit Metadata