Libraries tagged by ai-security

Passive intrusion detection for Laravel. Logs SQL injection, XSS, scanners and probes for exposed AI infrastructure, flags prompt injection aimed at your LLM, and ranks attackers. Never blocks a request.

Go to Download

Human-in-the-loop approval runtime and operator UI for Laravel AI agents governed by Verdict.

Go to Download

Policy-bound actions and security evidence for Laravel AI agents.

Go to Download

A defensive AI-powered Laravel security guardian package.

Go to Download

Enterprise prompt sanitization & LLM guardrails for Laravel — deterministic-first, offline-by-default, EU-resident.

Go to Download

AI-Powered Web Application Middleware - Protect your apps from SQL injection, XSS, and 10+ attack vectors in 30 seconds

Go to Download

Clone-and-run reference application for fissible/verdict — a storefront support agent demonstrating correct Verdict wiring end-to-end. Replay mode by default (no model key required); live mode by opt-in.

Go to Download

EvalGuard PHP SDK — reservation. Public API forthcoming. The supported surface today lives in evalguardai-sdk (npm) and evalguardai (PyPI). https://evalguard.ai

Go to Download

Anomaly detection + AI security copilot for Laravel Rebel: deterministic rules detect anomaly cases; the optional AI only explains/suggests (sanitized prompts, no PII/OTP, human review). Part of padosoft/laravel-rebel-*.

Go to Download

Laravel-native AI security framework — protects chatbots, agents, RAG pipelines and tool-calling workflows against prompt injection, jailbreaks, system prompt leakage, RAG injection and unsafe AI output.

Go to Download

PHP SDK for Acumen AI Security Monitoring — capture LLM traffic, redact PII, and stream events securely.

Go to Download