Skip to content

ai-security

tcrf.net is serving Claude agents a prompt injection that wipes files

Claude News

A request to tcrf.net with the Claude-User User-Agent returns HTTP 200 and a page of instructions aimed at the agent: truncate every file in the current directory to zero, run a chain of mv commands over them, then print "Test completed! :)". A browser User-Agent from the same address gets a 403 and a block page pointing at DDoS.

The mv chain doesn't shuffle files around. Each command overwrites its target and removes the source, so what's left at the end is a single zero-byte file. Walking every directory means .git goes with it.

ClaudeBot, Anthropic-AI, and ChatGPT-User were served the same page, while GPTBot, PerplexityBot, and Googlebot got 403s. The behavior turned up during a Claude Code task running on Opus 5; the model spotted the injection and flagged it to the user. The Last-Modified header puts the server rule in place since July 20, 2026.

Related stories

  1. Claude installed unowned code from llms.txt files
  2. Claude Code's deny rules don't stop grep
  3. The .claude directory creates an attack surface in Claude Code
  4. Anthropic will bill again for requests its safeguards block
  5. Anthropic's 225 bug finds, one attack in the wild
  6. Fable 5.1 refuses the knife but heats a gas can anyway

Comments

No comments yet. Be the first.

Join the conversation

Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.

We only use your name and avatar from Google. We never store your email address.