#owasp

SasanLabs/VulnerableApp

Java

93

health

OWASP VulnerableApp Project: Break it. Scan it. Reproduce it. Benchmark against it. Improve it.

Agent-Threat-Rule/agent-threat-rules

TypeScript

86

health

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP, FINOS & SigmaHQ. MIT-licensed.

PrismorSec/prismor

Python

86

health

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude,codex etc.)