AI Security Cybersecurity News

Latest News

Claude Code VS Code Extension Can Reach Files Beyond Trusted Workspaces, Researchers Find

Claude Code VS Code Extension Can Reach Files Beyond Trusted Workspaces, Researchers Find

RedSide Security November 16, 2026 AI Security 35 views

Researchers found the Claude Code extension for VS Code can prompt for access to a path that looks workspace-local while the real file sits outside it. Anthropic reviewed the report but does not treat it as a vulnerability.

Continue reading: Claude Code VS Code Extension Can Reach Files Beyo…
Amazon Exposes Self-Funding AI Agent Campaign Hunting API Keys in LiteLLM, Dify, and One API

Amazon Exposes Self-Funding AI Agent Campaign Hunting API Keys in LiteLLM, Dify, and One API

RedSide Security November 16, 2026 AI Security 63 views

Amazon's threat intelligence team used decoy servers to capture records of autonomous AI agents scanning for exposed LiteLLM, One API, and Dify instances, stealing provider API keys, and reusing them to fund further attacks.

Continue reading: Amazon Exposes Self-Funding AI Agent Campaign Hunt…
FBI Warns ARTEX AI Agents Are Compressing Break-In Times to Under Three Hours

FBI Warns ARTEX AI Agents Are Compressing Break-In Times to Under Three Hours

RedSide Security November 14, 2026 AI Security 81 views

The FBI's November 2026 FLASH alert warns that attackers are using ARTEX AI agents to chain stolen credentials, exposed apps, and cloud misconfigurations into privileged access in under three hours.

Continue reading: FBI Warns ARTEX AI Agents Are Compressing Break-In…
SGLang RCE Flaw Breached NEAR AI, Exposing Data From 18 Agents and ~100 Users

SGLang RCE Flaw Breached NEAR AI, Exposing Data From 18 Agents and ~100 Users

RedSide Security November 10, 2026 AI Security 841 views

An attacker exploited a remote code execution flaw in the open-source SGLang inference engine to compromise a NEAR AI server, potentially exposing requests — including those sent in confidential mode — and stealing data tied to 18 agents and about 100 users.

Continue reading: SGLang RCE Flaw Breached NEAR AI, Exposing Data Fr…
AI Agents, One Attacker, Seven Districts: The BOSSAI Breach of Taipei's Emergency Dispatch Records

AI Agents, One Attacker, Seven Districts: The BOSSAI Breach of Taipei's Emergency Dispatch Records

RedSide Security November 10, 2026 AI Security 147 views

A single attacker using BOSSAI AI agents accessed emergency dispatch records across seven Taipei districts and found a fire department platform exposing patient ECG data and ambulance video without a login, Acronis researchers say.

Continue reading: AI Agents, One Attacker, Seven Districts: The BOSS…
Claude Dispatch Abused by Malicious Browser Extensions to Execute Code Locally

Claude Dispatch Abused by Malicious Browser Extensions to Execute Code Locally

RedSide Security November 06, 2026 AI Security 113 views

Researchers at Forever Security demonstrated that a malicious browser extension with script access to claude.ai can abuse Claude Dispatch to make Claude Desktop execute code locally, and the underlying flaw remains exploitable.

Continue reading: Claude Dispatch Abused by Malicious Browser Extens…