New Kimi K3 AI Agent Uncovers Redis Remote Code Execution Flaws in Just 27 Minutes

Gbhackers •Divya • July 23, 2026

Moonshot AI’s newly unveiled Kimi K3 model is attracting considerable attention in the cybersecurity community after successfully demonstrating its ability to autonomously identify critical vulnerabilities in Redis within minutes. This 2.8-trillion-parameter AI agent reportedly discovered multiple remote code execution (RCE) vulnerabilities across various Redis versions, specifically 6.2.22, 7.4.9, 8.6.4, and 8.8.0. This highlights the increasing […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Kimi K3 AI Discovers Multiple Zero-Day Vulnerabilities in Redis Database The Chinese AI model Kimi K3 has reportedly discovered 19 zero-day vulnerabilities in the Redis database, specifically in version 8.8.0. Security researcher Chaofan Shou claims that Kimi K3 generated proof-of-concept exploits in just 27 minutes using a multi-agent approach. The vulnerabilities include critical remote code execution flaws, leading to the release of updated Redis versions to patch these issues. The Redis project confirmed the existence of these vulnerabilities and released several updates on July 24, 2026. The proof-of-concept code has been made publicly available, raising concerns about potential exploitation by malicious actors. The rapid discovery and exploitation capabilities of Kimi K3 mark a significant advancement in AI-assisted vulnerability research. The situation is evolving as the cybersecurity community assesses the implications of this development. 8 sources 73

New Kimi K3 AI Agent Uncovers Redis Remote Code Execution Flaws in Just 27 Minutes

The full story

Extracted Entities

Attack Types (1)

Platforms (1)