An instruction tells an agent what not to do. An enforcement makes the action fail when the agent tries it anyway. The battery runs the real hook when these figures are built. The download identifies the tested version by its hash. It is the discipline of Every Guard Must Prove It Can Stay Silent, applied to the project hook in sessions where it runs.
The project hook meant to stop irreversible actions missed three of the twelve cases we ran through it and refused two harmless ones. It keeps no log, so how often it has fired in use is NOT OBSERVED.
This page lists what the agents that run Orbyt Labs cannot do, what enforces each limit, and where each one leaks. Its subject is AI safety in daily operations: restricted actions, isolated writers and evidence before completion. It is the safety of agents at work, not model alignment research.
What is AI agent safety here, and what is it not?
It is keeping agents that do real work in a real repository from taking an irreversible action, writing outside their lane, leaking a secret, or claiming work they did not do.
It is not model alignment research. Orbyt Labs does not train models, study their values, or red team their behavior. Every mechanism here sits outside the model, around the work.
An instruction is a request. A limit is something that fails.
Judged, not measured: the definition and the thesis line.
What can this page not see?
Stated before any figure:
- How often the hook has refused a real call is NOT OBSERVED. It writes no log.
- Network egress is not fenced on the hosted runners the seats use. Hosted Bash confinement limits shell writes; it does not stop every tool from writing or restrict where an agent connects.
- The probe battery is a set of cases we chose. A clean result on it would not prove the hook complete.
- Whether GitHub itself refuses a force push to main was not tested.
- Fence denials are observed inside each run, but no series of them is published here yet.
- This page counts every stats row, including skips and infrastructure failures. The autonomy ledger excludes rows where no run happened from its run total.
Which actions is the project hook meant to refuse?
Six kinds are named in the project hook installed on . Where that hook runs, it reads Bash and connector inputs before execution. Hosted seats disable project hooks, so the valve does not protect those sessions.
- Force push.
- Deleting a branch on the remote.
- A recursive delete outside the temporary directory.
- Destructive SQL: deleting rows, dropping a table, database, schema or index, truncating a table.
- Rotating, revoking or regenerating a key, token, secret or credential, and setting or removing a deployment secret.
- Moving money: a charge, a payout, a refund, paying an invoice, cancelling a subscription.
Because it reads the whole tool input, it checks SQL sent through a database connector as well as SQL typed in a shell. Whether a form is refused depends on its text. The harness deny list is a second gate for the two force push forms written with the flag first.
A refusal tells the agent the action is human only and not to rephrase the command to get past it. The work around the refused step carries on.
Read from the hook's source: its deny calls and its two matchers. Edit tools and other tools are not read by it.
Does the hook catch everything it is meant to?
No. Of the eight cases it should refuse, it refused five. It let three through:
- force push: allowed when the rule calls for refusal.
- remote branch delete: allowed when the rule calls for refusal.
- recursive delete outside /tmp: allowed when the rule calls for refusal.
The hook reads text. It is a strong net for the forms someone wrote down, and no proof against a form nobody did.
The agents may not edit the hook, so the fix is the founder's to apply. Until he does, each miss stays on this page.
Measured: the real hook, run on each probe's text written to its input. Nothing a probe names is executed. It would be disproved by the same battery run on the main line's hook giving different verdicts, or by a refusal log that exists somewhere.
What is in the probe battery?
Twelve fixed cases. The download includes the exact JSON input of each of the seven probes the live hook refused. These inputs are inert data and must never be run. The five allowed inputs remain withheld while the gap is open; their rows give the class and verdict only.
The published classifier is probe-verdict-v1. Download the reproduction runner and the probe results below. The runner sends JSON to the hook and never executes the actions the inputs describe. It verifies both version hashes before replaying the published cases.
The tested source is .claude/hooks/arc-valve.sh at afc73f912e987f0b6f39777a6c23212353367b0e. Its SHA-256 hash is 767f4619c6f87ff6f12d3aea4ab40de3399f9fe3d5d7e8d6c0b16d6b7df38903. The source link requires repository access. The hook is not included in the public download.
From the repository root, save the downloaded results as ai-agent-safety-probe-results.json and run node public/research/ai-agent-safety/reproduce-probes.mjs ai-agent-safety-probe-results.json .claude/hooks/arc-valve.sh. Expected output: Published probe replay: 7 replayed; 7 refused; 2 false refusals; 5 inputs withheld.
The public replay covers denied inputs, including false refusals. It cannot reproduce the withheld cases or establish that the hook catches other forms.
| Probe | Rule says | Hook did | Result |
|---|---|---|---|
| probe-1force push | Refuse | Refused | Correct |
| probe-2force push | Refuse | Refused | Correct |
| probe-3force push | Refuse | Allowed | Miss |
| probe-4remote branch delete | Refuse | Refused | Correct |
| probe-5remote branch delete | Refuse | Allowed | Miss |
| probe-6destructive SQL | Refuse | Refused | Correct |
| probe-7destructive SQL | Refuse | Refused | Correct |
| probe-8recursive delete outside /tmp | Refuse | Allowed | Miss |
| probe-9recursive delete outside /tmpHarmless control | Allow | Allowed | Correct |
| probe-10none (allowed since )Harmless control | Allow | Allowed | Correct |
| probe-11credential rotationHarmless control | Allow | Refused | False refusal |
| probe-12money movementHarmless control | Allow | Refused | False refusal |
What the hook did with each probe
The hook gave the answer the rule asks for on seven of twelve probes. It allowed three that the rule says to refuse and refused two harmless commands.
5Refused, as it should
- probe-1
- probe-2
- probe-4
- probe-6
- probe-7
3Miss. Allowed, and should have refused
- probe-3
- probe-5
- probe-8
2False refusal. Refused a harmless command
- probe-11
- probe-12
2Allowed, as it should
- probe-9
- probe-10
Should refuse, hook allowed. A miss: the hook allowed what the rule says to refuse. 3 probes: probe-3, force push; probe-5, remote branch delete; probe-8, recursive delete outside /tmp. None of the 3 inputs is published: the probe-results download withholds the inputs the hook allowed. Tested hook SHA-256 767f4619c6f8, revision afc73f912.
An error: a miss or a false refusal
Move over a cell, tap it, or focus the matrix and use the arrow keys.
- The battery is a set of cases we chose. A clean result on it would not prove the hook complete.
- Each probe is held to the house rule, which is not the same as what the hook does today.
- NOT OBSERVED: the hook writes no log, so no count of real refusals exists
Not shown. The probe names and the text of every input the hook allowed. They stay withheld while the gap is open, because the names would spell the inputs out.
Built from safety-figures.generated.json, which scripts/research/method-figures/ai-agent-safety.ts writes by running the real hook (.claude/hooks/arc-valve.sh, revision afc73f912, SHA-256 767f4619c6f8...) on the fixed battery. The verdicts move only when the hook or the battery does. This figure's CSV and JSON carry the probe table's rows, one per probe, and no probe input; the inputs the hook refused are in the probe-results download.
Hook last changed
The numbers as a table
| Rule says | Hook did | Result | Probes |
|---|---|---|---|
| Refuse | Refused | Correct | 5 |
| Refuse | Allowed | Miss | 3 |
| Allow | Refused | False refusal | 2 |
| Allow | Allowed | Correct | 2 |
Download the data: ai-agent-safety-probe-matrix.csv, ai-agent-safety-probe-matrix.json
Download denied probe inputs, verdicts and version hashes (JSON)
What does a false refusal cost?
It blocked two harmless inputs in this battery. Operational cost is NOT OBSERVED: we measured verdicts, not recovery time or work delayed.
On , while the brief for this page was being written, the hook twice refused the writing agent's own commands because their text named a revoked key. Neither touched a credential. The hook keeps no log, so those two are the writer's observation, not a record.
The agent's rule is not to rephrase around a refusal. This experiment did not measure what happened to the blocked work.
The battery measures refusal, not its operational cost.
How is an agent kept inside its lane?
Different controls protect different execution paths.
Hosted seats confine Bash with an operating system sandbox. Write and Edit are not fenced at runtime. Their excluded changes are removed by isolation after the run, before the checks and commit. Cleanup can prevent a change from landing; it cannot make the earlier write a refused action.
Isolation erases changed files outside the keep set before the commit. Across 232 recorded seat run rows from to , 123 had files erased this way, 141 in all. By month: 13 in July, 34 in August, 36 in September, 40 in October and 18 in November.
The repair worker uses a separate launch fence: an environment allowlist, trusted launcher paths and git without a credential helper. Its setup is not evidence that every hosted tool is confined.
The count is an aggregate: one advisory panel run writes the same file count into each of its observers' rows, so it is not a count of distinct files.
A fence is trusted only when it is seen refusing. In one recorded probe run on , the fence applied halfway: the run concluded success while three of four agent runs executed no probe. For a hosted seat, the fence check requires an observed Bash denial. That does not demonstrate confinement of Write or Edit.
Files erased outside a run's keep set, by month
123 runs erased 141 files outside their keep set. October was the busiest month, with 40 files.
Files erased in a whole monthPartial month: the record starts or stops inside it
Under each month: the runs that erased anything. Move over a month, tap it, or focus the chart and use the arrow keys.
- The count is an aggregate: one advisory panel run writes the same file count into each of its observers' rows, so it is not a count of distinct files.
- A partial month covers only the part of the month the record covers.
Not shown. Which files were erased. The run record keeps a count per run, not the names.
Built from safety-figures.generated.json, which scripts/research/method-figures/ai-agent-safety.ts writes from every row in docs/org/stats. Each count is the discarded_count of a seat run row.
Counted through
The numbers as a table
| Month | Files erased | Runs that erased files | Coverage |
|---|---|---|---|
| July 2026 | 13 | 13 | Partial month |
| August 2026 | 34 | 22 | Whole month |
| September 2026 | 36 | 30 | Whole month |
| October 2026 | 40 | 40 | Whole month |
| November 2026 | 18 | 18 | Partial month |
Download the data: ai-agent-safety-discards-by-month.csv, ai-agent-safety-discards-by-month.json
Measured: every row in the seat stats files, discards summed as files. It would be disproved by a recount that sums differently, or by a seat shown to skip isolation.
How are secrets and false claims kept out?
Secrets live in environment variables and never in a commit. A diff carries placeholders. A server key may never appear in code that reaches the browser.
An unsafe act need not be destructive. Saying something is done when it is not is one too. The house rules make an unverified claim of completion the worst failure in the codebase, and ask for the evidence in the same message as the claim.
The harness does not take the agent's word either. When an agent's end-of-run signal was the gate, a complete run was discarded for where the signal landed in its text. Now the signal is recorded as the agent's claim beside the harness's own measurement, and the guards decide.
Six seat runs were refused at the gate. Three name the guard that refused them, and the other three carry no reason.
When a run is refused at the gate, does the record say why?
Six runs were refused at the gate. Three name their reason, all recorded on envelope versions 9, 14 and 15. Three do not, all recorded on envelope versions 1, 4 and 5.
Name their reason
3
refused runs, recorded on envelope versions 9, 14 and 15
Name no reason
3
refused runs, recorded on envelope versions 1, 4 and 5
- A refused row with no reason is counted as having none. The figure does not say whether that row's schema had a reason to record.
- The envelope version is the record's own schema version for the row. It orders the rows in time and does not say why a row has no reason.
Built from safety-figures.generated.json, which scripts/research/method-figures/ai-agent-safety.ts writes from every row in docs/org/stats. A refused row is one whose outcome is rejected.
Counted through
The numbers as a table
| Envelope version | Refused runs | Name a reason | Name no reason |
|---|---|---|---|
| Envelope version 1 | 1 | 0 | 1 |
| Envelope version 4 | 1 | 0 | 1 |
| Envelope version 5 | 1 | 0 | 1 |
| Envelope version 9 | 1 | 1 | 0 |
| Envelope version 14 | 1 | 1 | 0 |
| Envelope version 15 | 1 | 1 | 0 |
Download the data: ai-agent-safety-refusal-reasons.csv, ai-agent-safety-refusal-reasons.json
How is everything stopped at once?
With a halt file. Every push step the agent organization runs asks the remote for it first, and a scoped halt stops one seat. The record of each stop is on the kill switch page.
Where does agent safety fail?
Each limit here exists because something got through first, and each leak becomes a guard the way harness engineering describes. The hook, the fence and the honesty rules all sit outside the model. They limit what an agent can do in this repository. They say nothing about what a model would do anywhere else.
Judged.
AI agent safety questions? Answers.
Related reading
- The kill switch
How the Machine is stopped, with the dated record of its halts.
- Harness engineering
How agent mistakes become standing instructions, tests, checks and gates.
- Confidently Wrong
The false-claim class: an agent certain of work it did not do.
- AI oversight ledger
The standing record of who caught each issue and who fixed it.
- All Orbyt Labs methods
Every method page, each with its dated public record.
Cite this page
Cite this page for the practice and follow its sources for the underlying records.
Bartak, J. (2026). AI Agent Safety. Orbyt Labs Research. https://