Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
צוות CyberHub · לפני 1 חודשים · 1 דק׳ קריאה
TL;DR · בקצרה
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 Fire." It works against Anthro
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 Fire." It works against Anthropic's Claude Code and OpenAI's Codex when either is running in an autonomous mode that approves its own
---
🔗 לכתבה המלאה במקור: The Hacker News
> ℹ️ ידיעה זו נאספה אוטומטית ממקור חדשות סייבר אמין. כל הקרדיט למקור המקורי.
💬 תגובות (0)
התחברו כדי להגיב.
אין עדיין תגובות. היו הראשונים! 🙂
📰 עוד חדשות
Metabase SQLi zero-day exploited in customer data-theft attacks
A critical Metabase SQL injection vulnerability was exploited in zero-day attacks to breach customer instances in data theft attacks, known to impact Framework and Tally. [...]
Unlimited Technology Systems breach impacts 3.8 million people
Healthcare software company Unlimited Technology Systems reported that more than 3.8 million people were impacted by a data breach incident that occurred in October 2025. [...]
Nearly 800 Malicious npm Packages Deliver Cross-Platform RAT and Infostealer
A cluster of nearly 800 malicious packages has been published to the npm registry as part of a new campaign designed to deliver cross-platform malware targeting Windows, Mac, and Linux systems. "These packages appear to use AI slop squatted, or randomly generated typo-squatting p