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. Cloud SaaS, Hybrid VPC and 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.

HOL Guard is an open-source, local-first runtime security layer for AI agents and automation. It sits between any AI harness and the tools it wants to run, pausing risky package installs, secret reads, shell commands, and MCP changes for review before execution.

Customize hardcoded instructions for AI agents, append, prepend, or completely replace instructions. See the hidden text that gets sent on apps like Xcode. Force compatibility for legacy client applications.

Zero-trust runtime security & governance layer for autonomous AI agents — prompt injection firewall, PII masking, real-time policy enforcement.

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