Tagged articles

AI code audit

3 articles · Page 1 of 1

Aug 13, 2026 · Information Security

Anthropic’s Mythos AI Reveals Linux Eventpoll Race Condition (CVE‑2026‑43074)

The article provides an in‑depth technical analysis of CVE‑2026‑43074, a use‑after‑free race condition in the Linux kernel’s eventpoll implementation, detailing how Anthropic’s Mythos AI discovered the flaw, the underlying RCU‑based fix, its impact, exploitation constraints, and recommended mitigation steps.

AI code auditCVE-2026-43074Linux kernel

0 likes · 10 min read

Anthropic’s Mythos AI Reveals Linux Eventpoll Race Condition (CVE‑2026‑43074)

Java Companion

May 24, 2026 · Artificial Intelligence

How a Chinese Open‑Source AI Code Auditor with 6K Stars Uncovered 49 CVEs

DeepAudit, a 6K‑star open‑source AI code‑audit system, uses a four‑agent architecture and sandboxed PoC verification to automatically discover and confirm 49 high‑severity CVEs across popular projects, while offering both deep audit and instant analysis modes, but it faces model dependency, cost, and sandbox limitations.

AI code auditCVELLM

0 likes · 11 min read

How a Chinese Open‑Source AI Code Auditor with 6K Stars Uncovered 49 CVEs

Black & White Path

Feb 10, 2026 · Artificial Intelligence

Claude Opus 4.6 Finds 500 Zero‑Day Bugs Out‑of‑the‑Box, Redefining Code Audits

Anthropic’s Claude Opus 4.6 not only shattered AI benchmarks in coding, reasoning and search, but also, when sandboxed with standard fuzzers and debuggers, autonomously uncovered over 500 high‑severity zero‑day vulnerabilities—including a GhostScript crash and buffer‑overflow bugs—prompting a market sell‑off and raising both excitement and misuse concerns.

AI code auditAnthropicBenchmark

0 likes · 5 min read

Claude Opus 4.6 Finds 500 Zero‑Day Bugs Out‑of‑the‑Box, Redefining Code Audits