Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Odoo data-quality audit guide that keeps database writes gated behind explicit human approval.
Install this only for Odoo environments where you are comfortable letting the agent read data-quality evidence through odoo-mcp. Keep writes disabled unless needed, review each proposed batch carefully, and only confirm changes after checking the previewed record IDs and values.
The manifest description says to use the skill when the user asks to "check data quality" or "clean up data," which are broad natural-language phrases that could match many ordinary requests beyond this specific Odoo database audit workflow. The trigger guidance does not include exclusion conditions or negative examples to narrow when the skill should not activate.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Read-only by default; every write needs a fresh approval token and the
human's explicit confirmation for that batch.
- Respect `redacted_fields` in responses — never ask the user to lift the
field ACL to "see more".
- If a check errored (`summary.checks_errored`), say so — do not present a
partial audit as complete.
No suspicious patterns detected.