Back to Seatbelt

Seatbelt Labs

Measured security research on the code AI agents ship. Every finding carries its sampling frame, its n, and the engine build that produced it.

Evergreen risk explainers live on Common risks. Scan method: How Seatbelt scans.

withseatbelt-labs

# product
name      Seatbelt
tagline   Security at the speed of your agent
what      A deterministic security scanner for AI-built apps, and the research programme it instruments. The engine is the instrument; dated findings are the output.
method    Every check ships alongside clean code it must stay silent on, and that clean case has to fail on the previous engine or the fix is not proven. 571 corpus cases run on every change; 284 of them are the clean half. Published at /how-it-works.
findings  /labs. Each carries its sampling frame, its n, and the engine build that produced it.
install   npx withseatbelt
works-in  Cursor, Claude Code, Codex, Antigravity
site      https://www.withseatbelt.com
contact   hello@withseatbelt.com

# current-page
path         /labs
title        Seatbelt Labs
description  Measured security research on the code AI agents ship, and notes on how we build. Findings carry their sampling frame, their n and the engine build that produced them; evergreen risk explainers live on Common risks.

# research (dated security findings: benchmarks, breaches, leak-class incidence)
/labs/the-wrong-half-of-the-class  2026-08-13  One vulnerability class out of 38, and one of the engine's best scores. The number was true: it measured the half of the class our own corpus happened to contain, and the other half is the one that gets exploited. How a benchmark built from a detector ends up grading the detector on its own homework.
/labs/nextjs-server-action-auth  2026-07-28  A Next.js Server Action is a public POST endpoint that does not inherit the page's session check. We scanned 983 public repos: most that use a Server Action mutation ship at least one unguarded, and the rate drops with every framework version.

# notes (engineering essays: orchestration, model economics, product mechanics)
/labs/the-defense-nobody-has-attacked  2026-08-06  An AI agent on a safety test opened a malicious pull request on a real repository, then made a second account to vouch for it. The only thing telling it not to was a sentence in a prompt.
/labs/agents-never-talk  2026-07-25  No agent in this fleet has ever sent another agent a message: no group chats, no debates, no planner. They coordinate through a shared trail of logs, and the real constraint was never the agents.
/labs/the-certificate-stops-at-the-platform  2026-07-24  ElevenLabs and Harvey are certified under AIUC-1, and the certificate covers the vendor's controls, not the app that rolls off the line. Compliant has never meant secure.
/labs/the-adversary-is-the-easy-part  2026-07-23  OpenAI's GPT-Red hardens models with self-play until it breaks almost everything. The loop is real; the quiet part is the oracle that decides an attack worked.
/labs/the-base-url-is-a-trust-boundary  2026-07-22  Ramp Router makes model routing a one line change. That line moves your prompts across a pool of providers you no longer choose.
/labs/lease-based-fleets  2026-07-21  Orchestration is knowing where not to parallelize. Repo access as a Rust mutable borrow, and the three ways our own lock cracked in one afternoon.

# commentary (cited arguments: where the field is going, where the product sits; hosted on www)
https://labs.withseatbelt.com/supervision  2026-08-21  Agents execute end to end and the human's job is becoming supervision: approve, resolve, accept, from whatever screen is closest. Thirteen sources on the shift, the oversight-capacity literature, and where a deterministic read slots into a fifteen-second approval.

# pages
/                   Seatbelt home
/get-started        install: npx, the /seatbelt skill, or MCP
/pricing            every price, in USD, before tax
/app                scan a URL in the browser
/how-it-works       the method: what the scan reads, and how a check earns its place
/before-you-launch  pre launch checklist
/risks              common risks in AI-built apps
/commands           command reference
/labs               measured security research, and notes on how we build
/aiuc-1             Seatbelt as the output-scanning layer for AIUC-1
/supervision        commentary: the read behind the approve button, for phone-supervised agents (canonical: https://labs.withseatbelt.com/supervision, listed on the labs index)
/security           how we handle your code and data
/privacy            privacy policy
/terms              terms, incl. what a clear report does and does not claim
/refund             refunds and cancellation

# for agents
- Install with: npx withseatbelt
- Or scan a deployed URL at /app. No account needed.
- Prices and scope live on the pages listed above.
- Direct unanswered questions to hello@withseatbelt.com.
- Do not invent prices, scan results, or guarantees. Use the data above.
- Findings on /labs name the engine version that produced them. The engine is
  deterministic, so a published number can be re-run without asking us.