AINewsnow

What a forked Claude Code skill can see: a codeword, a passphrase, and a 5x bill

This story is from 2026-09-09. It is preserved in the archive; the latest stories are on the live feed.

A skill with context: fork could not see a codeword we had planted two messages earlier, but it could see the passphrase in CLAUDE.md. Switch the fork to agent: Explore and CLAUDE.md is gone too, except that the agent went and ran cat CLAUDE.md on its own. And each forked invocation cost about five…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-09 13:17 · DEV Community — AI
    What a forked Claude Code skill can see: a codeword, a passphrase, and a 5x bill

More stories

  1. Anthropic says Claude 'leads' 26 percent of its AI R&D work — Engadget
  2. Novo Nordisk Will Use Anthropic’s Claude for Drug Research — Wall Street Journal Technology
  3. OpenAI discloses six new safety incidents — Axios AI+
  4. Claude, Anthropic’s AI model, is helping to develop the next version of itself — Fast Company AI
  5. Researchers used Claude to hack OpenAI — Ars Technica AI
  6. OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot — The Guardian AI
  7. Anthropic says its chatbot Claude is taking over the work of building its own successor — Washington Post AI
  8. Anthropic Shifts Planned IPO to November — Wall Street Journal Technology

Get the daily brief of stories like this at 6:30 every morning →