Adversarial Security Review

Have the AI attack your own code: ranked vulnerabilities, a concrete exploit for each, and the fix.

Advanced1 min read

Customize

Fill these in and the prompt below updates as you type. Anything you leave blank stays as a placeholder.

Paste the code this should work on

What the AI would otherwise have to guess

Your prompt

Act as an application security reviewer. Find vulnerabilities in this code, ranked by severity.

{{code}}

Context: {{context}}

Check specifically for: injection (SQL/command/template), broken auth or missing authorization, sensitive data exposure, unsafe deserialization, and unvalidated input.

For each finding: the vulnerability, a concrete exploit, the severity, and the fix. If you find nothing, say so plainly.

Similar prompts

Production Readiness Review

A pre-ship review of security, error handling, scale, and observability — no style nitpicks.

Check the Diff Against the Plan

Audit finished work against the plan it was supposed to follow — gaps only, no style notes.

Review the Diff, Not the Repo

Keep review scoped to what actually changed — correctness issues only.

Test-Coverage Review

List the untested edge cases in a diff, then write the tests that would catch them.