The attack that hijacked Claude Code came through Sentry. Datadog, PagerDuty, and Jira have the same exposure.

Tenet Security hijacked Claude Code in 85% of tests via a fake Sentry error — no stolen credentials, no alerts. Datadog and ...

Clean GitHub repo tricks AI coding agents into running malware

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

Gemini's Error 1099 is locking users out, but this unofficial fix could help

Error 1099 is blocking Gemini for many users, especially on Pixel devices, but there's an unofficial fix that might help.
SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Hackaday

Chain-of-Thought Spoofing Targets Reasoning AI Models

Menell] have shown that AI Large Language Models (LLMs) can fail to correctly distinguish between different instruction ...

CISA: Windows BlueHammer flaw now exploited by ransomware gangs

CISA confirmed on Monday that ransomware gangs are now exploiting a Microsoft Defender privilege escalation vulnerability, dubbed BlueHammer, that has previously been abused in zero-day attacks.
Tech Times

OpenAI Silently Rolled GPT-5.6 to Some Codex Users: A Hidden Prompt Exposes the Swap

GPT-5.6 was already running in Codex for some users before OpenAI’s government-approved preview opened to partners. A ...