The Agent Skills Directory

[COMMAND_EXECUTION]: The skill integrates with a CLI tool named odoo-ai to perform security introspection tasks, such as dumping ACLs and record rules from an Odoo database (e.g., odoo-ai --db <DB> brief <model>) and validating Python source files for security best practices.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data from Odoo databases and source code files, creating an indirect prompt injection surface. (1) Ingestion points: database metadata and Python source files via the odoo-ai tool. (2) Boundary markers: no specific delimiters are defined in the instructions for tool output. (3) Capability inventory: the tool can read database state and trace model method execution. (4) Sanitization: the instructions do not explicitly mandate sanitization of the ingested data.

odoo-security