odoo-service
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python's
subprocessmodule across multiple scripts (server_manager.py,db_manager.py,docker_manager.py,env_initializer.py) to execute shell commands for managing Odoo server processes, PostgreSQL databases, and Docker containers. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it processes user-influenced data—such as project names, database names, and module names—which are then passed as arguments to management scripts and interpolated into shell commands.
- Ingestion points: User-supplied parameters via the agent's natural language interface (e.g., project names, module names, database identifiers).
- Boundary markers: Absent; the instructions do not define specific delimiters for separating user-provided data from command parameters.
- Capability inventory: The skill possesses the capability to write files, manage Docker containers, execute shell commands, and perform database operations (including password resets).
- Sanitization: The skill utilizes list-based
subprocesscalls to mitigate shell injection;db_manager.pyincludes basic single-quote escaping for SQL password reset operations, but lacks comprehensive input validation for all parameters. - [EXTERNAL_DOWNLOADS]: The
docker_manager.pyscript generates Dockerfiles that fetch thewkhtmltopdfpackage from its official GitHub repository releases, which is a standard requirement for Odoo's PDF reporting functionality. - [DYNAMIC_EXECUTION]: The skill dynamically generates several types of executable or configuration content, including Dockerfiles,
docker-compose.ymlfiles, and IDE-specific task/launch configurations for VSCode and PyCharm, based on the project context provided at runtime.
Audit Metadata