Secure Bulletin Navigating the cyber sea with knowledge
Home > Tag > AI security
#AI security

New T3MP3ST Framework Turns AI Coding Agents Into Autonomous 0-Day Hunters

6 July 2026  |  dark6  |  AI

T3MP3ST, a new open-source framework, turns AI coding agents like Claude Code and Codex into autonomous red-teaming operators, claiming strong results on benchmark suites and a set of...

>> read more

Malicious ClawHub Skills Compromise AI Agents With Hidden Backdoors — 247,000 Installs, $2.3M Stolen

30 June 2026  |  dark6  |  Malware

Researchers scanning 50,000 ClawHub skills — the official marketplace for the OpenClaw AI agent platform — found working remote control backdoors, credential stealers, and autonomous malware that installs...

>> read more

DifyTap: Critical Flaws in AI Platform Dify Allow Silent Wiretapping of AI Conversations Across 1M+ Apps

24 June 2026  |  dark6  |  Vulnerability

Researchers at Zafran disclosed four vulnerabilities in Dify — including two critical CVSS 9+ flaws — that let attackers silently intercept AI conversations across tenants, access private files,...

>> read more

AutoJack: A Single Malicious Web Page Can Hijack Your AI Agent and Execute Arbitrary Code

22 June 2026  |  dark6  |  AI

A critical three-vulnerability exploit chain called AutoJack allows a single malicious web page to hijack Microsoft AutoGen Studio's browsing agent and execute arbitrary code on the developer's machine,...

>> read more

Microsoft Warns: Claude Code GitHub Action Exploitable via Prompt Injection to Leak CI/CD Secrets

8 June 2026  |  dark6  |  Vulnerability

Microsoft Threat Intelligence disclosed a prompt injection flaw in the Claude Code GitHub Action that allowed attackers to access /proc/self/environ and steal API keys from CI/CD runners. Anthropic...

>> read more

OpenAI Launches ChatGPT Lockdown Mode to Block Prompt Injection Data Exfiltration

8 June 2026  |  dark6  |  AI

OpenAI has released ChatGPT Lockdown Mode, a new security feature that disables outbound network capabilities to cut off data exfiltration pathways exploited in prompt injection attacks. Available to...

>> read more

Critical HuggingFace Transformers Flaw CVE-2026-4372 Enables Silent RCE — 232 Million Installs at Risk

8 June 2026  |  dark6  |  AI

A critical RCE vulnerability in HuggingFace Transformers (CVE-2026-4372) allows attackers to silently execute code by loading a malicious AI model, bypassing the trust_remote_code=False security control. Over 232 million...

>> read more

Google Gemini Voice Assistant Hijacked via WhatsApp, Slack and SMS: Researchers Bypass All Google Defenses

5 June 2026  |  dark6  |  Vulnerability

SafeBreach researchers demonstrate how attackers can silently hijack Google Gemini through malicious payloads in WhatsApp, Slack, SMS, and other messaging app notifications, bypassing all of Google patched defenses...

>> read more