Meet autosp, your AI teammate
for verified security fixes

Works with the scanners you already run

Apply for the pilot
  • Semgrep
  • CodeQL
  • Snyk Code
  • osv-scanner

autosp is an AI teammate
that finds vulnerabilities, proves them
with a failing test, fixes them in
a sealed sandbox, checks every fix three ways
and waits for you to merge

Finding vulnerabilities is easy. Closing them is the work.

AUTOSP takes one finding from report to a pull request with proof. A person decides what merges.

  1. Find

    It scans the repositories you choose, or takes results from the scanner you already run.

    • Semgrep
    • CodeQL
    • Snyk Code
    • osv-scanner

    CWE-89app/repositories/invoices.py

  2. Reproduce

    An agent writes a test that exploits the finding. The test has to fail. No failing test, no patch.

    # the exploit, as a test
    def test_find_invoice_injection(client):
        r = client.get(INJECTION)
        assert r.status_code == 404

    1 failed in 0.21s

  3. Fix

    A second agent writes the smallest fix it can, in a sealed copy of your code.

    • No network
    • Read-only
    • Non-root
    - "… WHERE id = '" + invoice_id + "'"
    + "… WHERE id = %s", (invoice_id,)
  4. Verify

    Three independent gates check the fix. The agents can't see or change them.

    • The exploit test now passes
    • The full test suite passes
    • A fresh scan finds nothing new
  5. Review

    AUTOSP opens a pull request with the evidence and stops. Your reviewers merge it.

    Pull request #412Waiting for you

    Fix SQL injection in find_invoice

    MergeMerges made by autosp: 0

Three gates. Any one of them can send a fix back.

  1. The exploit fails now

    The test that failed before must pass on the patched code.

    before: failednow: passed

  2. So do the variations

    Attack variants run against the fix, judged by rules AUTOSP owns, not by the agent that wrote it. For SQL injection: 18 variants.

  3. Nothing else broke

    Your test suite still passes, a fresh scan no longer reports the finding, and your tests and CI are untouched.

    • Test suite
    • Fresh scan
    • Tests and CI untouched

If a fix can't be proven, AUTOSP says so. It's never called fixed without evidence.

AUTOSP never merges. Not even when every check passes.

  1. entry 41sha-256 9c1e…07ab
  2. entry 42previous 9c1e…07ab
  3. entry 43previous 4d82…f31c
Illustrative. Change any entry and the chain breaks.
  • Only the repositories you pick

    A GitHub App with four permissions: Contents, Pull requests, Checks and Metadata. It never asks for Administration, so it can't touch your branch protection.

    • Contents
    • Pull requests
    • Checks
    • Metadata
  • A sealed sandbox

    Every job runs with no network and a read-only file system, on a disposable copy that is deleted afterwards.

    • No network
    • Read-only
    • Non-root
    • Time limit
  • Little goes to the AI model

    It sees the finding and the specific files it needs, never your whole repository or your Git history.

  • Every step on the record

    An append-only log where each entry carries the fingerprint of the one before it, so a change can't go unnoticed.

Early results, on our test applications.

Verified fixes by run set
Run setDateVerified
SQL injection22 Oct 20265 of 5
Access control (IDOR)22 Oct 20265 of 5
Mixed run set2 Nov 202615 of 15

0 merges made by AUTOSP, and known-bad fixes rejected every time.

Read this before the numbers. These are test applications and a free development model, not customer code and not the production model. Small samples: an early signal, not a benchmark.

Try it on your own code.

For Python teams on GitHub, of 20 to 150 engineers, with no dedicated security engineer.

  • You sign a scope document naming the repositories
  • Your reviewers handle AUTOSP's pull requests
  • Your tests run offline

Nothing touches your code until you've signed a scope agreement.

Engineering team size

Questions teams ask.

Does AUTOSP replace my scanner?

No. Its job is closing findings, not finding more of them. Keep your scanner; AUTOSP fixes what it reports.

Can it merge by itself?

No. Not in any configuration. Your reviewers merge.

What does it cover today?

Python on GitHub: SQL injection, cross-site scripting, insecure direct object references and vulnerable dependencies. It works with Semgrep, CodeQL, Snyk Code and osv-scanner.

What if it can't fix something?

It says so: inconclusive, needs human review, or a recommendation clearly marked as advice.

Will a passing scan mean my app is secure?

No. "No findings from these scanners" is all a scan can say, and that's how AUTOSP reports it.

Your scanner did its job. Let's finish it.

Apply for the pilot