Catches security controls that are imported, configured, or defined but never actually wired up — the unique AI failure mode of code that looks secure but isn't. Strictly focused on the gap between declaring a security control and applying it.
16
Total Checks
2
Delivery Formats
3
Categories
1
Versions
Initial release
2026-04-08
Copy the prompt in your preferred format above.
Paste into your AI coding tool (Claude Code, Cursor, Bolt, etc.).
Let the AI run all checks. Review the structured JSON output it produces.
Submit the JSON telemetry block to AuditBuffet for scoring and benchmarks.
Paste your JSON telemetry to get scores and benchmarks.
Submit Results