Arcjet runtime security SDK for NestJS — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF

Pure prompt-injection classifier for OpenApe chat-bridge. Heuristic by default, pluggable LLM backend. Input: text + sender context. Output: { score: 0..1, reason? }.

Security boundary between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, sanitizes untrusted terminal output, audits every command.

ESLint plugin for Vercel AI SDK security — detects prompt injection, system-prompt leaks, hardcoded API keys, and unvalidated model output in generateText and streamText.

Secure runtime for AI agents - isolated sandboxes with network isolation, PII scanning, prompt injection defense, and egress filtering.

SoterAI helps protect n8n AI workflows by detecting prompt injection, jailbreaks, secrets, PII, and unsafe AI instructions.

Safety guardrails for Reactive Agents — prompt injection detection, PII scanning, and toxicity filtering

LLM-as-judge grader with prompt-injection defense and structured tool-use output

OpenCode plugin that detects prompt injection in tool call outputs using an LLM judge

MCP-native prompt-injection firewall and security proxy.

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Detect and strip malicious prompt injection, jailbreaking, and data exfiltration attempts from LLM inputs. Zero dependencies. Works in Node.js and browsers.

TypeScript-native guardrails engine for AI applications. Content safety, prompt injection detection, output validation, and intelligent rate limiting.

Pi extension: web_search and web_fetch with 8-stage prompt-injection sanitization and SSRF protection. Zero dependencies.

Prompt injection defense patterns for AI-powered applications

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Arcjet runtime security SDK for Fastify — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF

Pi extension: structured task list with live widget and system-prompt injection to prevent goal drift

AI security scanner and runtime enforcement for LLM applications — detects prompt injection, API key leaks, unsafe output, RAG poisoning, and agent hijacking in code and live traffic.

Specialized agent system for pi: task delegation, activation/deactivation, and system prompt injection via .md files.