#owasp

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 450 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.

Open-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.

nosql-sanitize is a lightweight and blazing-fast suite of tools designed to prevent NoSQL Injection attacks in Node.js applications. It recursively sanitizes user-supplied data to remove characters and patterns (like $ and control characters) used in malicious MongoDB queries.

🐍 Cascavel — The zero-friction offensive security engine. Automate Red Team scans, validate exposures (CTEM), and generate compliance reports in one command.

Local-first security recon that briefs your AI coding agent: facts + tailored probes, code-in / artifacts-out. No LLM, no server, no running app.

Lightweight security agent for Linux servers — SSH brute force, WAF, bot detection, Docker/Kubernetes native. Deploy via curl, Docker, Helm.