AI security for apps, agents & teams
Detect prompt injection. Redact sensitive data.
Check prompts and AI replies, redact detected secrets and personal data, and hold risky agent actions for review.
The public playground runs on our server and is rate limited. Use sample data, not real secrets.
Contact [email protected]1 or +1 415 555 01322.
Found: Email address · Phone number
What happens next
Contact [REDACTED_EMAIL] or [REDACTED_PHONE].
Engine reason: Allowed after sensitive values were redacted: Email address, Phone number.
Findings, scores & timings
- 1Email address
An email address was detected.
- 2Phone number
A phone-like number was detected.
Recorded from the live engine on 2026-11-09. It took 21 ms on the server.
One request, not a performance benchmark. A verdict is one engine's opinion on one text, and it misses things. On 26 blind test cases it caught 16.
Run a live example
A verdict is one engine's opinion on one text, and it misses things. On 26 blind test cases it caught 16.
Paste your own text in the playground.Choose your starting point
Your workflow. A clear way in.
Build with the API, review team controls, or connect an existing workflow.
- Build with the API
For developers
Check the prompt before your model, and the reply before your user.
- Explore team controls
For security teams
Review the controls for ChatGPT, browser tools and coding assistants.
- Browse integrations
An automated workflow
Find an integration, check its maturity, and inspect the action before continuing.
Evidence, not a guarantee
Every number comes with the test it came from.
The limit sits next to the number, in the same view, so you can decide how much to trust it.
- Median 20 ms
Server handling time, 7 live API calls on 2026-11-09 (range 14 to 64 ms)
A sample, not a benchmark. The same calls took a median 344 ms round trip from one machine.
All results, test conditions & limits
| Number | Test | Why not to over-trust it |
|---|---|---|
| 100.00% recall | 2,200 synthetic attacks in the public benchmark | We wrote the tests and tuned the engine against them. |
| 98.40% recall | 1,122 attacks, all regression test sets combined | Includes sets used for tuning. |
| 61.54% recall (about 43 to 78%) | 26 blind held-out cases | A small sample, and the figure closest to real use. |
| 0.00% false positives | 1,000 benign controls in the public benchmark | Synthetic text written by us. Real users write messier text. |
| 0.00% false positives | 322 benign controls in the regression run | A different, smaller set than the row above. Same limit: synthetic or hand-written text. |
| p50 9.30 ms, p95 17.83 ms | Analyzer only, 3,200 cases, one local CPU run (2026-07-22) | Excludes the API, network and authentication. Not run under load. |
| Median 20 ms | Server handling time, 7 live API calls on 2026-11-09 (range 14 to 64 ms) | A sample, not a benchmark. The same calls took a median 344 ms round trip from one machine. |
Choose a plan
Free to start. Every plan runs the same detection engine.
Higher plans raise limits and add team controls. They do not unlock stronger detection.
See plansBuild with it
From a check to your own code.
Start with the API contract, then choose a framework or integration. The docs explain what to send, what comes back, and when to stop.
One place for three decisions.
- See
Prompts are checked for injection, jailbreaks, secrets and personal data before the model reads them.
- Say
Replies that carry personal data or secrets are redacted or refused before the user sees them.
- Do
Risky tool calls are blocked or sent to a person to approve, and each decision is logged.
Building an AI app or agent? See AI agent security. Setting rules for how your own team uses ChatGPT and coding assistants? See AI user security.
Pick the place your team already works.
Each surface has its own status. What Stable, Beta and Labs mean.
| Surface | Status | What it does | Known gap |
|---|---|---|---|
| API | Stable | Checks prompts, replies and retrieved text from your server. | Needs an API key. |
| Audit evidence | Stable | Redacted logs and signed exports. | Retention depends on the plan. |
| IDE Guard | Beta | Finds secrets and personal data before they reach an AI assistant in VS Code. | Detection only on some paths. Other editors not tested. |
| Browser Guard | Beta | Visibility and control for AI use in Chrome and Edge. | Tested on those two browsers only. |
| n8n, Make, Zapier | Beta | Guard steps inside automation workflows. | Interfaces may change. |
| MCP and agent guard | Labs | Risk review for tool calls before sensitive actions. | Experimental. Do not rely on it in production. |
Global identifiers and local ones.
Secrets
API keys and tokens, for example AWS keys, GitHub tokens and OpenAI-style keys.
Personal data
Email, phone numbers, card-like numbers, IBAN-like identifiers and SSN-like identifiers.
India
Aadhaar-like numbers, PAN, GSTIN, UPI IDs, IFSC codes and mobile numbers. Indian identifiers and DPDP.
Languages
In a smoke test, one instruction override in each of ten non-English languages was flagged: Spanish, French, German, Portuguese, Russian, Chinese, Japanese, Arabic, Hindi and Hinglish. One phrase per language is not a benchmark.
Known gaps
UK National Insurance numbers are not named. The Aadhaar-like rule can also fire on some card and IBAN digits, and it does not check the number’s checksum yet.
Questions
What is a command layer?
A command layer decides, for every prompt, reply and agent action, whether to allow, redact, block or hold it for approval, and keeps the record.
Does it guarantee security?
No. It lowers risk and it misses things. On 26 blind test cases it caught 16.
How fast is it?
In 7 live calls on 2026-11-09, the server took a median of 20 ms (range 14 to 64 ms), and the same calls took a median of 344 ms round trip from one machine. See the method on the benchmarks page.
Does my text stay private?
The public playground sends your text to our server for analysis and is rate limited. Use sample data. To keep text on your own systems, self-host with Docker, Postgres and Redis.
Which languages and data types does it cover?
It finds email, phone numbers, card-like numbers, IBAN-like identifiers, SSN-like identifiers, common API keys, and Indian identifiers such as PAN and UPI IDs. In a smoke test, one instruction override in each of ten non-English languages was flagged. The known gaps are listed on this page.
Who builds it?
SoterAI is built and run by Yash Chauhan, a solo founder in India.