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.