odoo-frontend
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8). It ingests data from untrusted external sources, such as Figma design URLs and live website content (via Chrome DevTools), to generate Odoo templates and SCSS configurations.\n
- Ingestion points: Content is fetched from remote URLs in
scripts/figma_converter.pyand analyzed from live DOM structures inscripts/devtools_extractor.py.\n - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the AI to ignore instructions potentially embedded in the fetched design data.\n
- Capability inventory: The skill possesses extensive capabilities, including reading, writing, and editing the filesystem, and executing bash commands.\n
- Sanitization: Absent. The provided Python scripts do not perform validation or sanitization of the external data before it is interpolated into Odoo module files.\n- [COMMAND_EXECUTION]: The skill utilizes several scripts to perform its primary scaffolding functions. Notably,
scripts/theme_mirror_generator.pyperforms complex code modification on existing Python files using AST parsing and regular expressions. While aligned with the tool's primary purpose, this behavior represents a form of dynamic execution that relies on the integrity of the input files and user-provided configuration.
Audit Metadata