Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

by quikefix quikefix.com | Jul 13, 2026 | Uncategorized

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker’s code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls “Friendly...

GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents

by quikefix quikefix.com | Jul 13, 2026 | Uncategorized

Researchers at Wiz found that a flaw in six popular AI coding assistants lets a booby-trapped code project quietly take control of a developer’s computer. The assistant asks permission to edit one harmless-looking file, but the write lands on a sensitive one...

Fake 7-Zip Installers Turn Devices Into Residential Proxy Nodes

by quikefix quikefix.com | Jul 13, 2026 | Uncategorized

Cybersecurity researchers have disclosed details of a new threat actor dubbed Lurking Lizard that has been operating an end-to-end malicious residential proxy business using an infrastructure comprising more than 230 lookalike domains. The activity dates back to at...

AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers

by quikefix quikefix.com | Jul 13, 2026 | Uncategorized

Sophos looked at a week of its own endpoint data and found that AI coding agents such as Claude Code, Cursor, and OpenAI Codex are setting off detection rules written to catch human intruders. The agents are not malicious. They just do a lot of things that, to a...

New HalluSquatting Attack Could Trick AI Coding Assistants Into Installing Botnet Malware

by quikefix quikefix.com | Jul 13, 2026 | Uncategorized

AI coding assistants have a habit of making things up. Ask one to fetch a popular tool, and it will sometimes hand back a real-sounding name for a project that does not exist. New research, which its authors call HalluSquatting, turns that habit into an attack: work...