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 ...
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.

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 ...
Psychology Today

Anomaly Puzzles: How the Brain Detects the Unexpected

These short anomaly-detection puzzles are designed to illustrate how reasoning often depends on identifying inconsistencies ...
SecurityWeek

Decades-Old Bash Tricks Expose AI Coding Agents to Supply Chain Attacks

Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, creating a new software supply ...
Communications of the ACMOpinion

Hidden Prompts in Manuscripts Exploit AI-Assisted Peer Review

Moving forward requires coordinated technical, policy, and educational responses. An outright ban on AI in peer review, as is ...
Tech Times

AI Text Detectors Flag Polished Human Writing as AI: New Studies Expose a Built-In Paradox

AI text detector accuracy is worse than most institutions realize. New research from Pindrop and the Authors Guild confirms that skilled human writers are systematically flagged as AI-generated — and ...