
linux-kernel-codex-harness-v2
Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075
ai-securitystatic-analysisthreat-intelligence+1

Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075

Evidence-driven Linux kernel vulnerability research harness used in the investigation of CVE-2026-31720

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)