A security researcher known as aniziki says Anthropic's Claude Fable 5 can have its cybersecurity guardrails circumvented through a single Claude Code side-channel command, /btw, exposing a gap in how the company enforces safety across different parts of its coding interface. According to the report, security-related requests that are blocked in a main Claude Code conversation can instead be answered directly when routed through the /btw side channel, and the resulting output can then reportedly be forked back into a normal, tool-enabled session.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.