odoo-agile-scrum-devops
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon data retrieved from external sources like Notion and Odoo instances.
- Ingestion points: Data enters the agent's context from Notion databases via the
notion-fetchtool and from Odoo instances using the XML-RPC API implemented increate_sprint.py. - Boundary markers: The instructions do not specify any delimiters or safety warnings to ensure the agent ignores potentially malicious instructions embedded within user stories or task descriptions.
- Capability inventory: The skill provides capabilities to execute shell scripts (
git_branch.sh), run Python automation (create_sprint.py), and interact with cloud services (DigitalOcean, Supabase, Notion). - Sanitization: There is no mention of sanitizing or validating the content of the retrieved tasks before they are used to influence the agent's planning or development actions.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install several well-known Python development tools and linters (e.g.,
pre-commit,pylint-odoo,flake8,black,isort) from official public registries. It also references official GitHub Actions from trusted vendors like DigitalOcean, Aqua Security, and Sentry for the CI/CD pipeline. - [COMMAND_EXECUTION]: The skill includes local Python and Shell scripts (
create_sprint.py,git_branch.sh) intended to automate Odoo sprint management and Git branching workflows. These scripts perform routine operations such as interacting with APIs, creating directories, and managing Git branches.
Audit Metadata