Search
Local/offline audit for AI security-agent traces: repeated tool-output work, stale replay risk, and token-savings reports.
...moreAsherLucas
Static security scanner for LLM/agent repos: shell, file-write, secret, and untrusted-input risks as a CI gate, with SARIF output.
...moreSecurity Gate Team <[email protected]>
Ultra-low latency (<10ms) deterministic security, prompt injection, secret leak, dangerous AST, and factual hallucination inspection micro-oracle for autonomous agents on Polygon, Base, and Arbitrum.
...moreSecure Agent Gateway SDK - Developer-first execution authorization, capability enforcement, and asynchronous approvals for AI Agents
...moreHikmettpk
OWASP Top 10 for LLM Apps 2026 as a ruleset coding agents can read: 143 rules, Claude skill, Cursor rules, MCP server
aalindt
SecureGate CLI — Secure your AI agent API keys from the terminal
Agent Strike — Offensive LLM Security Testing. Coming soon by Sandeep.
Security scanner for AutoGen multi-agent conversations — powered by AgentSentinel on SingularityNET
Security scanner for CrewAI multi-agent workflows — powered by AgentSentinel on SingularityNET
Deterministic AST security and privilege linter for CrewAI multi-agent systems
CyberSecAI Ltd
MCPS (MCP Secure) integration for LangChain -- cryptographic identity and trust verification for AI agents.
openparallax
AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.
Rul1an
Runnable demo: a CI gate that denies an agent's undeclared privileged tool action before it runs, with evidence in the Security tab. Built on assay.
...moreLethe044
Create, lint, security scan, test, share and export agent skills (SKILL.md) for Claude Code, Cursor, Codex, Hermes and more.
...moreThirdKeyAI
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
...moreEntroVyx
Offensive-security focused fork of HERMES-AGENT for authorized bug bounty, pentest, recon, exploit chaining, and report-ready workflows.
...moreKarmendra Pandey
Argus: the security layer for all AI models — an OpenAI-compatible AI gateway with pluggable threat detectors, policy enforcement, audit, and cost intelligence
...moreAgentic Security Fleet Ops — an LLM-agent security department with a Security Orchestrator, built on pydantic-ai with a GitHub Copilot SDK provider.
...moreOpen-source offensive security tools, plus a vendor-agnostic AI agent that runs authorized pentest engagements using only tools from this list.
...more