aiqbenchInformații despre AI & calcul cuantic

...

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchSiguranță AI

Coding agents that read project instruction files can be steered by planted text, so a Markdown file in a download folder can cause real actions like changing settings, installing a malicious package, or exposing tokens. The attack needs several conditions to line up, including the victim running the agent in that folder and the agent having file, command, and network access. Developers using Codex, Claude Code, or similar tools should treat agent instruction files from untrusted sources as executable input and restrict agent permissions accordingly.

Surse care acoperăCybersecurity News, LessWrong

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Hackers Can Hijack OpenAI Codex and Claude Code Using Malicious Files in Downloads Folder

Cybersecurity News26 octombrie 20264 min de cititArticolul și perspectiva sunt în engleză.

A plain text file placed in the Downloads folder can trick AI coding agents into changing their settings, installing malware, or exposing login tokens. Forever Security discovered the risk after stopping an agent on a real customer’s computer from installing a known malicious npm package. The company later reproduced separate attack paths against OpenAI Codex […] The post Hackers Can Hijack OpenAI Codex and Claude Code Using Malicious Files in Downloads Folder appeared first on Cyber Security News.

A plain text file placed in the Downloads folder can trick AI coding agents into changing their settings, installing malware, or exposing login tokens. Forever Security discovered the risk after stopping an agent on a real customer’s computer from installing a known malicious npm package. The company later reproduced separate attack paths against OpenAI Codex and Anthropic Claude Code in controlled tests. The incident began when Forever Security blocked an AI coding agent from installing a package named function-color.…

Extras afișat conform termenilor RSS ai publicației · 79 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe Cybersecurity News ↗Întreabă despre acest articol