Scope
Whether the code is in the scoped asset at the deployed revision, whether the class is excluded, and whether every clause of the chosen impact row has an artefact behind it.
- Binding table
- Exclusion matches
- Impact row, clause by clause
Give it your draft, code and programme rules. Get a verdict, the main blocker and the quickest fix.
US$10 per month. Runs on your own model and key.
Built by Tradi3, 77th on Immunefi’s all-time leaderboard on 10 October 2026: 2nd of 133 in the Firelight competition, 8th of 65 in Quantus and 15th of 186 in ENS, with 17 valid Critical submissions, the most on the board.
The seizure bug is in the code. The proof reads the return value of liquidate on a mock oracle; the impact row names the borrower’s collateral.
Scope, provenance and prior art end a report without a proof. They run before the stages that cost you work. Each stage reads the output of the stages before it.
Whether the code is in the scoped asset at the deployed revision, whether the class is excluded, and whether every clause of the chosen impact row has an artefact behind it.
Who performs each step, whether the behaviour is documented design or an audit fix, whether the bug adds anything over the intended path, and whether every precondition is reachable from live state.
Whether a known issue, a prior audit note, a team branch or your own earlier report has the same root cause or the same one-line fix.
Whether the proof runs production code on every step and ends by reading the object the impact row names, with measured numbers.
The highest row of the programme’s own scale that the proof fully asserts, after every downgrade clause.
The one sentence that closes this report in ten minutes, and whether the first paragraph already answers it.
Whether the claims follow from the code, the proof is inline, the form and the body agree, and the limits are stated.
Which verdict the report gets.
A draft claims a Critical pool drain in Brinewell Lend, a lending protocol invented for this page. Eight stages later the finding stands, the severity moves, and one test is missing.
The seizure bug is in the code. The proof reads the return value of liquidate on a mock oracle; the impact row names the borrower’s collateral.
| Stage | Its verdict | What it decided |
|---|---|---|
| 1Scope | Its verdictSubmit | What it decidedThe file and the function exist in the scoped asset at the deployed revision. No exclusion names the class. |
| 2Provenance | Its verdictProve first | What it decidedEvery step is performed by an unprivileged liquidator. The unhealthy state is set through MockOracle.setPrice, with no route from live state shown. |
| 3Prior art | Its verdictSubmit | What it decidedAudit item L-04 has the same symptom and a different root cause, so it is not a duplicate. Naming the difference in the first paragraph goes in To do. |
| 4Proof | Its verdictProve first | What it decidedThe final assertion reads the return value of liquidate. The impact row names the borrower’s collateral. |
| 5Severity | Its verdictRewrite, then submit | What it decidedThe proof supports High on the scale supplied. The draft selects Critical. |
| 6Triager | Its verdictProve first | What it decidedFastest close: impact not shown. “The attacker drains the pool” has no assertion behind it. |
| 7Report | Its verdictRewrite, then submit | What it decidedRoot cause and fix are confirmed against lines 215-216. The title claims a pool drain; the code shows a loss per position. |
| 8Verdict | Its verdictProve first | What it decidedOne fork test stands between this draft and a High. |
liquidate sizes the seizure from the whole collateral, not from the amount repaidA liquidator who repays 1 unit of debt on an unhealthy position takes all of its collateral. The borrower loses the collateral above the debt. Bound: each unhealthy position’s collateral, minus the debt repaid.
liquidate checks one thing about the position: _healthFactor(p) < WAD (line 214).seized from p.collateral and bonusBps. repay is not in the expression.seized at p.collateral, so any repay above zero seizes the whole collateral.repay and send seized to the caller.function liquidate(address borrower, uint256 repay) external nonReentrant {
Position storage p = positions[borrower];
if (_healthFactor(p) >= WAD) revert Healthy();
uint256 seized = (p.collateral * (BPS + bonusBps)) / BPS;
if (seized > p.collateral) seized = p.collateral;
p.debt -= repay;
p.collateral -= seized;
debtToken.safeTransferFrom(msg.sender, address(this), repay);
collateralToken.safeTransfer(msg.sender, seized);
}
The position is unhealthy. The borrower was going to lose that collateral to liquidation anyway.
OpenThe intended path seizes the repaid amount plus the bonus. The draft never shows the two outcomes side by side, and its test reaches the unhealthy state through MockOracle.setPrice.
Compute seized from repay: convert it to collateral at the oracle price, add bonusBps, then cap at p.collateral.
Run the fork test with both assertions, then paste the command and its output into the report body.
| # | Action | Artefact it produces | Stage |
|---|---|---|---|
| 1 | ActionRerun the test on a fork of the deployed revision, with the price moved by the real feed. | Artefact it producesCommand and output | StageProof |
| 2 | ActionAssert the borrower’s collateral balance before and after, and add the full-repay control. | Artefact it producesTwo assertions | StageProof |
| 3 | ActionChange the claimed severity to High and quote the impact row word for word. | Artefact it producesEdited report | StageSeverity |
| 4 | ActionName audit item L-04 in the first paragraph and state the different root cause. | Artefact it producesOne paragraph | StagePrior art |
| 5 | ActionReplace “drains the pool” in the title with the per-position loss. | Artefact it producesEdited title | StageReport |
The run asks for the evidence that decides outcomes. Anything you leave empty is marked as not supplied in the result.
Your report, the source files it cites and the proof with its command and output.
The programme’s impact list, the row you intend to select, the exclusions and the trusted roles.
The programme’s own scale with its thresholds and downgrade clauses, pasted in.
The scoped asset, the revision your proof ran against and the revision that is deployed.
Known issues, audits and fix-review notes, team branches, and your own earlier reports on the programme.
The date you first reproduced it, the fee and duplicate rules, and what the platform stored after you filled in the form.
The Gauntlet is eight reviews, run in order from your browser on your own key.
Each stage is its own review type. It goes through our server, which adds the method of the stage, to your provider. Your provider bills each call to your key.
A stage’s output goes to the later stages as a file named stage-<n>-<profile>.md, next to your draft and your code.
A cancelled run, a provider error or a reload keeps every stage that finished. The run picks up at the stage that did not.
It downloads with a SHA-256 hash of every file the run read.
The Gauntlet is part of Operator at US$10 per month, including US$2 Bounty Operator API credit per paid month. A run is eight reviews on your own model, so your provider bills eight model calls to your key.
The one you choose, on your own API key: OpenRouter, Anthropic, OpenAI, Google Gemini, xAI, DeepSeek, Mistral, Groq, Infron, OrcaRouter or Bounty Operator. Your files and key pass through our server, which adds the method of each stage. No file, key or review is stored.
The stages need an API key. The report stage is the Challenge a draft report review, which also works on its own in ChatGPT or Claude. From a coding agent, the gauntlet prompt of the MCP server runs the same order: seven hosted reviews through run_review with a connection token, and the report stage on your agent’s own model.
The run stops there. If scope, design intent or prior art says drop or likely duplicate, the run stops before you spend time on a PoC, and the result opens on that verdict. A button runs the remaining stages anyway.
It reads the files you supply. The proof stage reads your test and its output and tells you the one run that is missing. You run it locally.
The example on this page, and 1 review a day of any review type. Every gauntlet stage except the final verdict is also a review type you can run on its own.
Unlimited reviews, the Gauntlet, Panel review and 4 reviews at once.
Billed monthly. Cancel any time in the Stripe portal and keep access until the paid period ends.