Anthropic’s Claude Fable 5 Prompt Leak and Export-Control Shutdown Expose AI Security Risks

Anthropic’s Claude Fable 5 faced twin security and policy controversies after a publicly surfaced 3,826-line system prompt revealed detailed behavioral rules, safety controls, tool use, memory handling, refusal logic, and prompt-injection defenses for the model inside the Claude app. Reporting said the prompt appeared to come from a public GitHub repository rather than a network intrusion, and described Fable 5 as Anthropic’s first public Mythos-class model, with high-risk cyber, bio, and chemistry requests reportedly routed by classifiers to Opus 4.8 and stronger safeguards separating Fable from the more capable Mythos line.

At the same time, U.S. authorities imposed an unprecedented export-control restriction after alleging a jailbreak in Fable 5 could expose advanced cyber capabilities associated with Claude Mythos 5 or Mythos Preview, forcing Anthropic to suspend access for foreign nationals worldwide and then shut access more broadly until mitigations were deployed. Anthropic and outside experts reportedly disputed the severity of the flaw, but access was only gradually restored after the company blocked the jailbreak, while analysts said the action introduced a novel theory that commercial AI model access can constitute an export and raised concerns that frontier AI services may now face sudden regulatory, geopolitical, and availability disruptions.