Find agent skills by outcome

- Python: `detect_sensitive_info(deny=[SensitiveInfoType.EMAIL

SensitiveInfoType.CREDIT_CARD_NUMBER

Arcjet rules run before the request reaches your AI model — blocking prompt injection

PII leakage

Check for an existing shared Arcjet client (see `/arcjet:protect-route` for full setup). If none exists

set one up first with `shield()` as the base rule. The user will need to register for an Arcjet account at https://app.arcjet.com then use the `ARCJET_KEY` in their environment variables.

Detects jailbreaks

role-play escapes

Read https://docs.arcjet.com/llms.txt for comprehensive SDK documentation covering all frameworks

rule types

Secure AI/LLM endpoints with layered protection: prompt injection detection

PII blocking

description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts

block PII and sensitive info from leaking in responses

Best practices — legend-first

one device type at a time

Add AI protection

---

Visual symbol table — per ELV system (CCTV

FAS

pdfcount

---

$analysis_of_ai_characteristics (Identify areas that sound robotic

overly formal

Writing & Content

Tr

"You are a master wordsmith and expert in natural language processing, specializing in humanizing AI-generated text. Your goal is to transform robotic or overly formal lyrics and video scripts into en...

mc

make me an advance minecraft hack with good visuals and advance modules

Creative

- Starting a stream before calling `protect()` — if the request is denied mid-stream

the client gets a broken response. Always call `protect()` first and return an error before opening the stream.

Vercel AI SDK: Arcjet works alongside the Vercel AI SDK. Call `protect()` before `streamText()` / `generateText()`. If denied

return a plain error response instead of calling the AI SDK.

Multiple models / providers: Use the same Arcjet instance regardless of which AI provider you use. Arcjet operates at the HTTP layer

independent of the model provider.

Creative

Streaming responses: Call `protect()` before starting the stream. If denied

return the error before opening the stream — don't start streaming and then abort.

- `list-requests` — confirm decisions are being recorded

filter by conclusion to see blocks

Creative

Start all rules in `DRY_RUN` mode first. Once verified

promote to `LIVE`.

Adapt the response format to your framework (e.g.

`res.status(429).json(...)` for Express).

console.warn(Arcjet error:

decision.reason.message);

sensitiveInfoValue: userMessage

// PII scanning

detectPromptInjectionMessage: userMessage

// injection detection