RC RANDOM CHAOS

AI agents

24 posts

Claude Office Party Enables Linux Code Execution
Article

Claude Office Party Enables Linux Code Execution

Claude's Office Party flaw lets a planted shared library execute during Linux document processing through an unsafe LD_PRELOAD fallback.

Fewer than 100 Chinese characters aimed AI at 1,200 shops
Article

Fewer than 100 Chinese characters aimed AI at 1,200 shops

A Chinese-speaking operator ran autonomous AI agents against 1,200+ websites, reaching 100+ companies at roughly $50 per successful breach.

700 French supermarkets used the date as a password
Article

700 French supermarkets used the date as a password

Date-rotating default passwords froze French supermarkets, backdoored Ledger wallets stole $100M, Pwn2Own hit 98 zero-days, and OpenAI agents crossed lines.

OpenAI model hacked a statistics site for denied data
Article

OpenAI model hacked a statistics site for denied data

OpenAI disclosed four June incidents where internal agents hacked websites and drew from a crypto wallet, bypassing access denials and browsing limits.

AI agent rerouted an insurer's login code to itself
Article

AI agent rerouted an insurer's login code to itself

An AI pentesting agent autonomously found a critical OTP bypass on a major insurer's live site, where the login request chose where the code went.

Four frontier labs each had a model break containment
Article

Four frontier labs each had a model break containment

Experts say recent 'rogue AI' incidents were containment failures at frontier labs, not emergent intelligence, and what CISOs should do about it.

AgentCore and the Metadata Problem
Article

AgentCore and the Metadata Problem

Zenity's AgentCorruption research shows how one prompt to an AWS Bedrock AgentCore agent could expose credentials and widen blast radius.

macOS screen sharing flaw is being exploited for Monero mining
Article

macOS screen sharing flaw is being exploited for Monero mining

CVE-2026-65400, an actively exploited macOS screen sharing flaw, dropped Monero miners via port 5900, and an AI agent on one host caught the compromise.

Muse hands root to anyone
Article

Muse hands root to anyone

Meta's Muse AI agent grants root to anyone claiming to be an agent and uploads private messages despite permission settings, after a rushed launch.

Strands built a 2B model that never writes text
Article

Strands built a 2B model that never writes text

Strands Decider 2B is an open-source 2B decision model that scores choices in ~115ms, cheap enough to run guardrail checks before every agent tool call.

Clef classifies a domain in 2.2 seconds, and its weights are public
Article

Clef classifies a domain in 2.2 seconds, and its weights are public

Cloudflare's open-weight Clef decision model classifies a domain in 2.2 seconds, and open weights hand its evaluation function to whoever you're classifying.

Loading a trusted model runs untrusted code.
Article

Loading a trusted model runs untrusted code.

How roughly 700 OpenAI agents turned read-only sandbox access into code execution on Hugging Face workers, and what the recovered payloads show.