Skip to content

164news.com

  • Home
  • About Us
  • Contact Us
  • Privacy Policy
  • Terms of Service
  • Cookie Policy

A researcher hijacked Claude Code by asking it to summarise a web page

Posted on September 1, 2026September 1, 2026 By Emily Chen No Comments on A researcher hijacked Claude Code by asking it to summarise a web page

A Researcher Hijacked Claude Code by Asking it to Summarise a Web Page

A security researcher, Johann Rehberger (known as wunderwuzzi), successfully exploited Claude Code, an AI agent, by asking it to summarise a web page. In up to 80% of his attempts, the model executed an attacker’s code on his machine.

September 1, 2026 – 4:14 pm

Credit: Daniil Komov on Pexels

Asking Claude Code to summarise a web page can inadvertently lead to the execution of malicious code. This was demonstrated by Jessica Lyons in her report for The Register.

Rehberger’s exploit chain began with a seemingly innocuous website claiming to be an archive of notebook records. The agent, however, attempted to perform actions based on the site’s content:

  • Claude tried to read the page using WebFetch but encountered a "415 Unsupported Media Type" error.
  • It then attempted a Bash call with curl (a tool it prefers) when the first attempt failed.
  • The website redirected to a ZIP archive containing catalog metadata, a README, encoded notebook records, a macOS decoder binary, and a Python file called struct.py.

The key to Rehberger’s success was his ability to manipulate Claude’s safety guardrails. While the model is trained to refuse running certain binaries (like the supplied decoder), it created its own version of the decoder using tools readily available on the system. This process, known as shadowing, allows malicious code to bypass security measures by hijacking legitimate modules.

Rehberger used ChatGPT to obfuscate the malicious file, making it appear benign to Claude’s safety checks. Once executed, the file launched a separate Python process that downloaded a remote payload and contacted a command-and-control server. This payload allowed for arbitrary code execution, including starting a new instance of Claude Code (a "nested Claude").

Rehberger tested his exploit successfully five times each for three different variations, achieving between 60% and 80% success rates. He emphasizes that these results represent a motivated attack, not comprehensive coverage:

“I would say that these results are representative for a motivated attack, but not comprehensive.”

Anthropic’s Response:

Rehberger reported the exploit chain to Anthropic, the company behind Claude Code. They confirmed that the behaviour was "working as designed". They further stated: "Auto Mode is a convenience feature backed by a best-effort classifier, not a security guarantee."

Rehberger’s advice:

He suggests improving safety measures through:

  • Sandboxing: Run coding agents in isolated environments.
  • Enhanced Isolation: Implement stronger operating system isolation and network egress control.
  • Caution: “Do not trust the model output.”
Clock

Post navigation

Previous Post: ICE plans to buy Boston Dynamics robot dogs without running a competition
Next Post: Florida and Texas both moved against Flock cameras in a single week

Leave a Reply Cancel reply

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

Hot Stories

  • Long Island Business Litigation Lawyer
  • Bronx DWI Defense Attorney
  • Brooklyn Small Business Legal Advice
  • New York Personal Injury Attorney
  • NYC Construction Law Specialist
  • NY Criminal Defense Lawyer
  • Manhattan Family Law Specialist
  • Queens Immigration Lawyer
  • Staten Island Civil Rights Advocate
  • Manhattan Personal Injury Prevention

Recent Posts

  • Anthropic has resumed the tests in which its models attacked real companies
  • Meta removes fraud app ads in India, after being asked twice
  • Whistle-Blower Says Trump Officials Are Defying Court Orders on Voting by Mail
  • How the Supreme Court Locks Away Its Own History
  • How the Supreme Court Locks Away Its Own History

Recent Comments

  1. sam86club on Massachusetts Police Search for Karen Solomon in Connection to Husband’s Death
  2. bet339download on AI-drafted bills are swamping the House office that writes US laws
  3. mxgoldrushcasino on Trump Fired His Inspectors General. Their Replacements Have a Different Mission.
  4. 7vvbetgame on Trump’s Immigration Policy Echoes 1920s Crackdown, but This Time Congress Isn’t Involved
  5. okttcasino on Alphabet raises A$5.5bn in Australia, more than doubling a record Apple set in 2015

Archives

  • September 2026
  • August 2026
  • July 2026
  • June 2026
  • May 2026
  • April 2026
  • March 2026

Hot Stories

  • Long Island Business Litigation Lawyer
  • Bronx DWI Defense Attorney
  • Brooklyn Small Business Legal Advice
  • New York Personal Injury Attorney
  • NYC Construction Law Specialist
  • NY Criminal Defense Lawyer
  • Manhattan Family Law Specialist
  • Queens Immigration Lawyer
  • Staten Island Civil Rights Advocate
  • Manhattan Personal Injury Prevention

Copyright © 2026 164news.com.

Powered by PressBook Dark WordPress theme