CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool injection, hardcoded secrets, and DMCA-flagged AI dependencies.
An open-source knowledge base of defensive countermeasures to protect AI/ML systems. Features interactive views and maps defenses to known threats from frameworks like MITRE ATLAS, MAESTRO, and OWASP.
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
AspGoat is an intentionally vulnerable ASP.NET Core application for learning and practicing web application security.
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
AIGoat - Open-source AI security playground for LLM red teaming. AI Goat provides hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.
The open-source agent firewall. Prevent AI agents from leaking data, using dangerous tools, and importing poisoned dependencies.
A low-cost approach to testing AI chat experiences and security concepts
🛡️ A firewall for your agent's brain. Open-source security proxy that protects AI agents from prompt injection attacks. 4-stage pipeline, community threat feed, no bypass mode.
Complete security layer for OpenClaw - CLI Scanner + Live Dashboard. Secrets detection, config hardening, prompt injection scanning, MCP server auditing. Zero telemetry.
Passive LLM Conversation Capture & Sensitive Data Exposure Research
Open-source AI security firewall. 81 engines for PII detection, prompt injection defense, MCP security, and egress classification. Local-first. Zero cloud dependency.
The most comprehensive open-source mapping of OWASP GenAI risks to industry frameworks - 70 mapping files, 25 frameworks, 1,016 controls, 125 incidents, ML classifier pipeline. Source lists: LLM Top 10, Agentic Top 10, DSGAI 2026. EU AI Act, NIST, ISO, SOC 2, FedRAMP, DORA, OT/ICS, MITRE ATLAS.
Vanguard is an Office 365 Add-in for advanced email scanning to prevent malicous attacks on an enterprise scale
LLM-powered SSH/Telnet honeypot (on Cowrie) that analyzes attacker intent in real time, generates intent-tailored responses to prolong engagement, and logs everything - breaking the honeypot trilemma at low cost. Computer Networks 2026.
Free security & privacy scanner for AI-coded apps. 766 rules, 84 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for leaked keys, open databases, and injection holes in 5 seconds.
One-liner for AI solo developers to fasten the security bolts on their systems
Open source security for LLM inference
own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, same verdict, no model in the decision path. 100% recall / 100% precision on a 298-sample corpus, scored in CI against live rivals. Claude Code hook or MCP proxy.
Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.
Add a description, image, and links to the llm-security topic page so that developers can more easily learn about it.
To associate your repository with the llm-security topic, visit your repo's landing page and select "manage topics."