
awesome-ai-security
A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

An autonomous reflective Go agent for full-cycle security auditing, WAF evasion, OOB LDAP verification, self-remediation (auto-patching), and…


Enrolled agent can smuggle arbitrary OpenSearch _bulk operations via DataValue.index. GHSA-ff9g-85jq-r3g3. Draft

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.

Official repository for CTFTiny

CVE-2021-44228

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes,…

CVE-2025-62215 exploit development using Claude Code Agent Team

AURORA demo target — deliberately vulnerable lockfiles (CVE-2019-10744, CVE-2018-18074, CVE-2020-26160)

A Docker based LDAP RCE exploit demo for CVE-2021-44228 Log4Shell

A Vagrant VM test lab to learn about CVE-2021-38647 in the Open Management Infrastructure agent (aka "omigod").

CVE-2021-44228 漏洞复现完整记录(含环境搭建、触发验证)

PoC for CVE-2023-22496: Netdata Agent <1.37 OS Command Injection via registry_hostname

AI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.