— Product

Three capabilities. One agent. Zero day-rate.

Discovery maps your perimeter every week. Scanner pentests it monthly and revalidates open findings weekly. Shield watches the wire between scans. One model, one memory — yesterday's recon hit becomes tomorrow's chain root.

01 / Scanner

Active probes that chain like a human.

An autonomous Claude-powered agent reasons across findings (auth bypass, IDOR, SSRF, deserialisation, business logic) and stitches them into multi-step attack chains. Every chain ships with a reproducible PoC you can hand to engineering and run in CI. Runs monthly per project; weekly revalidation replays open findings on the same cadence.

  • OWASP Top 10 + business logic + race conditions
  • Authenticated runs (cookie, bearer, OAuth, SAML)
  • Replayable curl / HTTP scripts attached to every finding
  • CVSS, CWE, CVE, OWASP 2021 + PCI DSS 4.0 mapped automatically
  • Safe-by-default: rate-limited, scoped, no DoS, no destructive payloads
aisec · pentest · app.aisec.tools
$ aisec pentest --target app.aisec.tools
▸ recon.subdomain     found 7 hosts (1 new: staging-2)
▸ probe.auth          → JWT alg=none accepted
▸ probe.idor          → /api/users/:id leaks email
▸ chain.compose       2 → 3 → privilege_escalation
▸ verify.takeover     200 OK [CRITICAL]
▸ poc.write           poc-2891.curl (1.2 KB)

FND-2891-014  Account takeover
              CVSS 9.1 · CWE-287 · auth-bypass
— How the agent thinks

One loop. Five steps. Always running.

Memory carries between cycles: yesterday's recon hit becomes tomorrow's chain root.

01
Recon
map & fingerprint
02
Probe
test hypotheses
03
Chain
compose findings
04
Verify
prove with PoC
05
Report
ship + revalidate
memory carries forward · 24h cycle · resumes mid-chain
— What onboarding looks like

Five minutes from sign-up to first chain.

No agent install. No SSO ticket. Verify ownership via a DNS TXT record and the agent goes to work — Discovery first, then Scanner against everything it found.

01 / Sign up
Email + OTP

Passwordless. No card to start a trial scan against demo targets.

02 / Add target
Project & root domain

Subdomains inherit the project's authorisation. Test creds optional — improves auth coverage.

03 / Verify
DNS TXT challenge

HMAC-signed token at _aisec-verify.<root>. One-shot. Subdomains inherit.

04 / First scan
Discovery → Scanner

Discovery enumerates the perimeter; Scanner pentests it. First findings land in your dashboard within the hour.

05 / Triage & close
Mark fixed → retest

"Ready to retest" reruns the exact PoC against the patch. Reproduces → reopen. Doesn't → resolve. Audit-grade evidence either way.

— Built on

The stack that makes the agent work.

No black box. AISEC orchestrates a small, deliberate set of best-of-breed tools — and the agent is the one deciding what to run, when.

Reasoning core

Claude Sonnet for Scanner. Haiku for Discovery, Retest, Revalidation.

The model picks attack strategy from recon data, writes payloads, reads responses, and decides when a finding is real. Tool calls are typed, sandboxed, and observable. Heavy reasoning on Sonnet; cheap revalidation runs on Haiku — same agent loop, sharper unit economics.

Browser layer

Playwright with stealth fingerprints + HAR capture.

Renders SPAs, follows fetch / XHR, captures every API call the browser made. Mines source maps for hidden endpoints, classifies links (interesting / auth / api / files), runs auth-bootstrap registration end-to-end with email-OTP solving.

Recon stack

Custom recon + nmap + nuclei (auto-matched).

CT-log harvest, passive DNS, port scans, WAF fingerprint, OpenAPI/GraphQL schema mining, JS source-map sink mining, npm vuln audit. 10K+ nuclei templates auto-selected to detected tech stack — no manual template wrangling.

Exploit toolbelt

sqlmap · nikto · ffuf · jwt_tool · ssrfmap · commix.

The agent reaches for the right tool when its hypothesis says so — not by template, by reasoning. Plus a built-in differential-test tool that fires N request variants and compares timing / status / body diff to confirm a finding before reporting.

Intel feeds

CVE / NVD / ExploitDB · LeakCheck · HIBP.

Continuously refreshed CVE feed for retro-scanning new vulnerabilities against your existing inventory. Credential-leak intelligence cross-references your domain against breach databases, then probes login endpoints.

Reporting

PDF reports + JSON evidence bundle + dashboard.

Every finding gets a reproducible PoC, CVSS, CWE, OWASP 2021 + PCI DSS 4.0 + CWE Top 25 mapping, and exploitability score (0–100). Reports white-label on Pro and above.

Integrations

Plugs into the tools your team already lives in.

$_
CLI
aisec scan, aisec replay — single binary, scriptable.
GH
GitHub Actions
Block PRs that introduce regressions — gate by severity.
JR
Jira / Linear
Findings open as tickets with PoC, owner, SLA timer.
SS
SAML SSO
Okta, Azure AD, Google Workspace · SCIM provisioning.
PD
White-label PDF
Customer-ready audit reports under your brand.
SL
Slack
Critical alerts in 90 seconds · channel per severity.
WB
Webhooks
JSON events for SIEM, SOAR, custom dashboards.
{}
REST API
Read findings, trigger scans, export evidence.
PG
PagerDuty
Critical chain → on-call, with PoC attached.
DR
DataDog
Stream metrics + finding events into your obs stack.
Coverage

Speaks every layer of your stack.

The agent fingerprints what you ship and adapts its playbook accordingly. If we're missing something you need, ask — playbooks are added in days, not quarters.

See it run against your stack.

Point it at one target. We'll show you the first chain before tomorrow's standup.