AI Security Assistant
An assistant that reads your findings, not the internet's guesses
On the Team plan, ask questions about any monitored asset: what to fix first, what a finding means, how to remediate. The assistant only receives your stored findings, components and local vulnerability records, must cite them, and any identifier it mentions that is not in that context is flagged as unverified.
What the inspector checks
Grounded answers
Context is limited to the asset's tracked findings and vulnerability records from the platform's database.
Prioritisation
Weighs CISA KEV, EPSS, exposure, severity and fix effort.
No invented CVEs
Every CVE or advisory ID in an answer is checked against the context; unknown ones are flagged.
Who uses it
- Triage after a large dependency scan
- Explaining findings to non-specialists
- Drafting remediation tickets
AI Security Assistant FAQ
Is my data used to train models?
Requests go to the configured provider under its API terms; AI Inspector Lab does not use your data for training.
Other detectors
Try the AI Security Assistant for free
Check text, public websites and GitHub repositories for free - no account needed. Go Pro for private document, image and code inspections, Compare and the API.