secprbench
secprbench/secprbenchBenchmark of 265 real vulnerability-introducing code changes across nine C, C++, and Rust projects, with paired review tasks, Docker sandbox, judge,…
ai-securitycode-analysiscurated-resources+6
secprbench/secprbenchBenchmark of 265 real vulnerability-introducing code changes across nine C, C++, and Rust projects, with paired review tasks, Docker sandbox, judge,…
dovughs/velum-vmmWindows x64 research hypervisor using Intel VT-x and per-CPU EPT hooks to intercept Nt/Ex/Mm routines, apply request policies, and stream live kernel…
asngs/agenttriage-open-sourceCross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…
seclog-open/seclogCollects multi-source security logs from reproducible Docker attack scenarios, builds attack chains, and provides the SecLog-Bench-216 benchmark for…
kavryxdev-group/sandboxed-untrusted-code-execution-runnerExecutes untrusted Python, JavaScript, and Bash in a hardened jail with 5-second, 128 MB, 0.5-core, PID and output limits.
neo23x0/process-watcherA process monitoring tool that tries to detect exploitation
gach0ng/agentstalkerEnd-to-end security audit framework for LLM agents: static AST and taint modeling, attack synthesis, Docker sandbox replay, and deterministic verdict…
anthropics/oss-scannerService that builds enrolled open-source repositories in isolated offline VMs and scans them for security vulnerabilities, emailing findings with…
darthton/hyperboneMinimalistic VT-x hypervisor for Windows x64 providing syscall, MSR, IDT, and kernel inline hooks plus EPT-based page substitution and TLB splitting.
abraxas/gatexFortinetHunter (@YogSoth0) binary cracking application. Part of CTF for FortinetHunter. ELF door: a stripped Nuitka onefile, an XOR-scrambled…
opposum0112/cusimanseComposable research-contract and YAML-recipe framework for agent-operated security experiments on disposable compute
joseluispino/hardstopReference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…
navikt/cpltSandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level…
top-celestial-company-ltd/dros-vep-liteOpen-source, 100% reproducible AI Agent Runtime Security Benchmark & Sandbox Environment (RFC-010 Draft Protocol).
saina15/cve-2020-14343-labControlled vulnerability research and reproduction lab for CVE-2020-14343 in PyYAML
shivammittal2403/cve-2026-59827-metabase-cyber-rangeEducational cyber range for CVE-2026-59827 (Metabase H2 unsafe deserialization / CWE-502). Isolated Docker lab — training only, not for attacking…
shivammittal2403/cve-2026-80428-ctfContainerized educational CTF lab emulating CVE-2026-80428 (CWE-502 deserialization) for safe, isolated student and researcher practice.
off-by-1-labs/flawedFix-Like Artifacts With Embedded Defects