Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets

A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source code, and customer data without ever sending one obviously harmful instruction.

The trick can work even after a blunt version of the same theft is refused: split the request into fragments that each look routine, place them in channels the assistant already uses, and let

Source: The Hacker News

Tags:

Leave a Reply

Your email address will not be published. Required fields are marked *

Explore More

WhatsApp is Finally Getting Usernames to Help Keep Phone Numbers Private

WhatsApp is Finally Getting Usernames to Help Keep Phone Numbers Private WhatsApp on Monday officially announced the start of global reservations of usernames with an aim to protect the privacy

Read More

Researcher Publishes GitLab RCE PoC Letting Authenticated Users Run Commands as Git

Researcher Publishes GitLab RCE PoC Letting Authenticated Users Run Commands as Git Security researchers at depthfirst published working exploit code on July 24 for a GitLab flaw that GitLab patched six

Read More

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet

Read More