
Agentic-Vulnerability-Discovery-and-Validation-Harness
Agentic harness that automates vulnerability discovery and validation, orchestrating AI-driven analysis workflows to confirm exploitable findings.

Agentic harness that automates vulnerability discovery and validation, orchestrating AI-driven analysis workflows to confirm exploitable findings.

Open reference implementation of the VEP protocol (RFC-010): a deterministic sandbox and benchmark suite evaluating AI agent runtime containment…

Zapscape (CVE-2026-64561) KVM/x86 shadow MMU UAF guest-to-host escape PoC mirror — V4bel/@v4bel, MIT; for authorized security testing

Security scanner auditing Claude Code environments for CVE-2026-21852 pre-trust execution, hook hijacking, and eBPF lockdown.

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Benchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…

Composable research-contract and YAML-recipe framework for agent-operated security experiments on disposable compute

RuralShield — an AWS CDK research prototype for healthcare cloud security, with policy-bounded AI triage, human-approved response, audit logging, and…

Self-service pentest platform that only scans domains whose ownership is proven, and re-checks that proof at scan time. OWASP, TLS, DNS and port…