[tag]

#ai-agent

5 stories

[research]Sep 22, 2026By ByteBulletin Editor

Meta Muse zero-day exposes agent token to local apps

A vulnerability in Meta's new AI assistant allows any local macOS command to hijack the agent's authentication token, undermining its privacy claims and prompting Amazon to block the service.

[tooling]Aug 20, 2026By ByteBulletin Editor

OpenFOAM Agent: An AI Research Assistant for CFD Simulation Workflows

A new open-source agent framework aims to make OpenFOAM more accessible by automating setup, case preparation, and post-processing through natural language.

[tooling]Aug 6, 2026By ByteBulletin Editor

Prime Intellect launches Prime Agent, a self-improving coding harness built on recursive sub-agents

The open-source harness swaps fixed tool schemas for a persistent IPython kernel and lets agents refine their own prompts, skills, and memory mid-task.

[tooling]Jul 22, 2026By ByteBulletin Editor

Hugging Face Breach: Internal Datasets and Credentials Compromised, Users Urged to Rotate Keys

Attackers exploited a vulnerability via a malicious dataset upload, gaining elevated access to Hugging Face's internal systems before being detected by the company's own AI-powered anomaly detection.

[tooling]Jul 18, 2026By ByteBulletin Editor

Talon: A multi-platform AI agent harness with pluggable backends and MCP tool access

An open-source agent runtime that runs across Telegram, Discord, Teams, terminal, and desktop, with a modular architecture supporting five different AI backends and MCP-based tools.