AI-Infra-Guard
tencent/ai-infra-guardA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
ai-securitycloud-securitycontainer-security+7
4.5k
tencent/ai-infra-guardA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
9bie/php2shell-bypass-aslr-expPure-HTTP exploit achieving RCE on PHP 8.4.26 + Apache mod_php via session upload_progress heap leak, dangling pointer reuse, and ASLR bypass to call…
huhusmang/awesome-llms-for-vulnerability-detectionThe community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…
google/kernel-researchLinux kernel exploitation toolkit providing an exploit-building library, ROP chain and stack pivot generators, kernel image runners, and a target…
owasp/owasp-top-10-neocloud-and-ai-data-center-security-risksOWASP framework cataloging the top 10 security risks in neocloud and AI data center infrastructure, covering hardware, networking, isolation,…
slowmist/knowledge-baseCurated knowledge base of blockchain security research, audit reports, guides, and translations covering smart contracts, cryptography, and AI…
joseluispino/hardstopReference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…
top-celestial-company-ltd/dros-vep-liteOpen reference implementation of the VEP protocol (RFC-010): a deterministic sandbox and benchmark suite evaluating AI agent runtime containment…
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
cr0nx/awesome-linux-attack-forensics-purplelabsThis page is a result of the ongoing hands-on research around advanced Linux attacks, detection and forensics techniques and tools.
safety-research/red-teaming-auto-modeResearch code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…
trailofbits/polytrackerAn LLVM-based instrumentation tool for universal taint tracking, dataflow analysis, and tracing.
owasp/ai-threat-modelerOWASP project for AI-assisted threat modeling, helping teams identify, analyze, and document security threats and mitigations in system designs.
penberg/chimeraSandbox untrusted code with safe access to the host.
owasp/secure-headers-projectOWASP knowledge base and validator for HTTP security response headers, providing recommendations, statistics, and automated configuration checks.
facebook/mcpguard-dynamicKernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)
markakd/container_escapeContainer escape proof-of-concept exploits for CVE-2026-80521 and CVE-2026-52910, with a disposable QEMU/Ubuntu VM harness for safe PoC execution.