General
PromptBeginner5 minmarkdown
Detects jailbreaks
role-play escapes
0
Explore
Find agent skills by outcome
118,785 skills indexed with the new KISS metadata standard.
Showing 24 of 118,785Categories: Data, General, Creative, Communication
General
PromptBeginner5 minmarkdown
Read https://docs.arcjet.com/llms.txt for comprehensive SDK documentation covering all frameworks
rule types
0
General
PromptBeginner5 minmarkdown
Secure AI/LLM endpoints with layered protection: prompt injection detection
PII blocking
0
General
PromptBeginner5 minmarkdown
description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts
block PII and sensitive info from leaking in responses
0
General
PromptBeginner5 minmarkdown
Best practices — legend-first
one device type at a time
0
General
PromptBeginner5 minmarkdown
Add AI protection
---
0
General
PromptBeginner5 minmarkdown
Visual symbol table — per ELV system (CCTV
FAS
0
General
PromptBeginner5 minmarkdown
pdfcount
---
0
General
PromptBeginner5 minmarkdown
$analysis_of_ai_characteristics (Identify areas that sound robotic
overly formal
0
General
PromptBeginner5 minmarkdown
mc
make me an advance minecraft hack with good visuals and advance modules
0
Creative
PromptBeginner5 minmarkdown
- 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.
2
Data
PromptBeginner5 minmarkdown
- Sensitive info detection runs **locally in WASM** — no user data is sent to external services. It is only available in route handlers
not in Next.js pages or server actions.
3
General
PromptBeginner5 minmarkdown
**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.
3
General
PromptBeginner5 minmarkdown
**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.
3
Creative
PromptBeginner5 minmarkdown
**Streaming responses**: Call `protect()` before starting the stream. If denied
return the error before opening the stream — don't start streaming and then abort.
3
General
PromptBeginner5 minmarkdown
- `list-requests` — confirm decisions are being recorded
filter by conclusion to see blocks
3
Data
PromptBeginner5 minmarkdown
If the user wants a full security review
suggest the `/arcjet:security-analyst` agent which can investigate traffic
0
Creative
PromptBeginner5 minmarkdown
Start all rules in `DRY_RUN` mode first. Once verified
promote to `LIVE`.
0
General
PromptBeginner5 minmarkdown
Adapt the response format to your framework (e.g.
`res.status(429).json(...)` for Express).
0
General
PromptBeginner5 minmarkdown
console.warn(Arcjet error:
decision.reason.message);
0
General
PromptBeginner5 minmarkdown
sensitiveInfoValue: userMessage
// PII scanning
0
General
PromptBeginner5 minmarkdown
detectPromptInjectionMessage: userMessage
// injection detection
0
General
PromptBeginner5 minmarkdown
return Response.json({ error: Forbidden }
{ status: 403 });
0
General
PromptBeginner5 minmarkdown
const decision = await aj.protect(req
{
0