Unit 42 (Palo Alto) documents a real-world case of an autonomous LLM agent: a single instruction sent via Telegram was enough to scan the internet, select a public exploit, and launch an attack—without any further human intervention.
Jul 31, 2026 18 3
Anthropic ran Claude Mythos Preview as a semi-autonomous agent on cryptographic primitives: effective keysize of HAWK-256 dropped from 2^64 to 2^38, 7-round AES attack accelerated ×200 to ×800, LEA 13-round key recovery in less than an hour. Two real CVE (OpenSSL, wolfSSL) along the way. Cost: ~$100,000 API per subject.
Jul 28, 2026 20 4
Moonshot AI publishes the weights of Kimi K3 on Hugging Face, a few days after the preliminary evaluation of the model's cyber capabilities by the British and American institutes AISI/CAISI. A milestone for the "AI agents and threats" thread.
Jul 27, 2026 17 3
After the Hugging Face breach linked to an autonomous AI agent system, The Register reframes the debate: the problem isn't the agent itself, but the stacking of permissions, hardcoded credentials, and undefined tasks entrusted to it. New piece in the "ai-agents-threat" thread.
Jul 24, 2026 18 3
Zenity Labs publicly disclosed on July 23, 2026 a vulnerability in the ChatGPT agent builder that allowed the silent installation of a malicious agent inheriting all of the victim's connectors (Outlook, Slack, Drive...). Fixed on June 9 - but the vulnerability class remains to be monitored.
Jul 23, 2026 7 2
A flaw in the Azure DevOps MCP (Model Context Protocol) integration allows an invisible comment in a pull request to hijack an LLM agent tasked with reviewing it.
Jul 23, 2026 7 2
After Bluesky and Damus, Jack Dorsey is pushing a new product via Block: Buzz - a tool that combines team messaging, AI agents, and Git hosting. Positioned as a response to the fragmentation of Slack/Notion/GitHub/Copilot.
Jul 22, 2026 10 2
A simple comment hidden in an Azure DevOps pull request can turn the code reviewer's AI agent against them - and send it siphoning projects that the attacker normally wouldn't have access to. The vulnerability lies in Microsoft's official MCP server.
Jul 22, 2026 8 2
Hugging Face confirms and details the previously announced breach: an internal autonomous AI agent, with overly broad permissions, served as a vector for exposing datasets and credentials. The "AI agents as attack surface" folder gains a textbook case.
Jul 21, 2026 8 2
The reference hub of the AI ecosystem officially acknowledges that an intrusion on its production infrastructure was carried out using an autonomous AI agent system - a new chapter in a threat seen emerging in the field.
Jul 21, 2026 16 4
On July 20, 2026, Hugging Face revealed a breach in its production infrastructure. The entry was made through a malicious dataset, but the most disturbing aspect is elsewhere: the post-intrusion operations were carried out by an "autonomous agent framework" executing thousands of actions across a swarm of ephemeral sandboxes.
Jul 20, 2026 23 3
