security-harness
dmdhrumilmistry/security-harnessMulti-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…
ai-securitycode-analysisdevsecops+9
43
dmdhrumilmistry/security-harnessMulti-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…
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…
lfi-project/lfiTop-level repository for LFI: Practical, Efficient, and Secure Software-based Sandboxing
anthropics/oss-scannerService that builds enrolled open-source repositories in isolated offline VMs and scans them for security vulnerabilities, emailing findings with…
michaels1011/ephemora-cellCapability-based WASM runtime for executing untrusted AI-generated code with enforced CPU, memory, time, I/O, and filesystem limits. Provides…
githubsecuritylab/seclab-taskflowsExample AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…
getkern/kernRootless container runtime and sandbox that launches kernel-enforced OCI images in milliseconds with no daemon, featuring resource profiles, seccomp…
penberg/chimeraSandbox untrusted code with safe access to the host.
facebook/mcpguard-dynamicKernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)
patriksimek/vm2Isolated JavaScript sandbox for Node.js that runs untrusted code with restricted access to built-in modules and host resources via Proxy-based…
beelzebub-labs/beelzebubA secure low code deception runtime framework, leveraging AI for System Virtualization.
harbor-framework/terminal-bench-2Benchmark for evaluating AI agents on real-world tasks including vulnerability resolution, code debugging, and protein assembly in containerized…
sinakarvandi/hypervisor-from-scratchSource code of a multiple series of tutorials about the hypervisor. Available at: https://rayanfam.com/tutorials
finbarr/yoloboxLet your AI go full send. Your home directory stays home.
pauldechassey/cve-2026-21636Proof-of-concept demonstrating a Node.js permission model bypass (CVE-2026-21636) that allows network access via undici/fetch to local services,…
v4bel/zapscapePoC exploit for CVE-2026-64561, a KVM/x86 shadow MMU use-after-free enabling guest-to-host escape with kernel root code execution on the host.
nishitm/goboxGO sandbox to run untrusted code
abhishek2512mishra/claude-code-security-auditSecurity scanner auditing Claude Code environments for CVE-2026-21852 pre-trust execution, hook hijacking, and eBPF lockdown.