Apps tagged with 'prompt-injection'

The industry standard for Provenance & Intent Contracts (PIC) in Agentic AI. Bridging the Causal Gap in autonomous systems.

BreachLab is a gamified AI security training game where you learn prompt injection techniques by trying to extract secret codes from 10 AI characters.

Open-source AI firewall and LLM proxy that redacts PII, blocks prompt injection, and enforces spend budgets before requests reach any AI provider. Apache 2.0, self-hostable.

Pipelock is an open-source agent firewall written in Go. It runs as a sidecar or local service between an agent and the network, scanning HTTP, WebSocket, and Model Context Protocol traffic through an 11-layer pipeline.

An AI security testing platform for LLM applications that detects prompt injection, jailbreaks, and data leakage using 650+ real-world attack vectors aligned with the OWASP Top 10 for LLMs.

AI firewall that detects prompt injection attacks and redacts PII/PHI with compliance context (HIPAA, GDPR, PCI). Single API endpoint with sub-100ms response time.

AI Agent Security Testing — 112 attacks across 14 categories. Prompt injection, jailbreaks, MCP poisoning, agency hijacking & more. Test any AI agent in 5 minutes.