# Fable 5 jailbreak wasn't unique: it worked on eight frontier models

> Anthropic's later investigation found the Fable 5 jailbreak worked on eight frontier models, including GPT-5.5 and Kimi K2.7.

*The brief: the flaw that pulled Claude offline was industry-wide, Anthropic's own investigation found.*

By The FeaturedDaily Desk · FeaturedDaily
Canonical: https://featureddaily.com/news/frontier-jailbreak-universal-brief

> **Key:** The security flaw that got Claude Fable 5 pulled offline on 12 June wasn't Anthropic's alone. The company's own investigation, reported in early July, found the same cyber jailbreak worked on eight frontier models, including OpenAI's GPT-5.5 and Moonshot's Kimi K2.7.

## What happened

The US used export controls to take Claude Fable 5 and Mythos 5 offline on 12 June 2026, after Amazon researchers found a way past Fable 5's safeguards to identify software vulnerabilities — in one case producing demonstration exploit code. The models stayed dark for more than two weeks. During the standoff, cybersecurity experts wrote an open letter arguing the flaw was not unique to Anthropic, and Anthropic's subsequent investigation confirmed it: the same bypass worked on Claude Haiku 4.5, Sonnet 4.6, Opus 4.6, 4.7 and 4.8, plus GPT-5.4, GPT-5.5 and Kimi K2.7.

> Axios's behind-the-scenes account of how the world's top AI models were revived detailed the safeguards Anthropic added to get Fable 5 back online — a new classifier, a draft severity framework and a researcher bounty.
> — [Axios](https://www.axios.com/2026/07/03/anthropic-ai-models-revived-behind-the-scenes), 2026-07-03

## The catch

The eight-model list came from Anthropic's investigation reported in early July, not from anything known on 27 June — at first, experts only argued the flaw was shared. The point stands: if a jailbreak spans the whole frontier, switching off one lab fixes little, and open-source advocates warn it simply pushes the same capability to cheaper open-weight models that face no export order.

> The Hill reported that the administration's restrictions on private AI models were already turning attention toward open-source systems, which face no equivalent gatekeeping.
> — [The Hill](https://thehill.com/policy/technology/5952253-trump-administration-ai-restrictions-opens/), 2026-06-30

## What's next

To restore its models, Anthropic trained a new classifier to block the technique, published a draft 'AI jailbreak severity framework', and opened a HackerOne programme for cyber-jailbreak reports. The episode is feeding Washington's push toward voluntary pre-release testing standards for frontier models — the shared-defence approach the industry-wide flaw seems to demand.

## Key takeaways

- Amazon researchers found a jailbreak in Claude Fable 5 that produced demonstration exploit code, triggering the 12 June US export-control order.
- Anthropic's subsequent investigation, reported in early July, found the same bypass worked on eight frontier models — not just Claude.
- Affected: Claude Haiku 4.5, Sonnet 4.6, Opus 4.6, 4.7 and 4.8, plus GPT-5.4, GPT-5.5 and Kimi K2.7.
- To get its models back, Anthropic built a new classifier, published a draft jailbreak severity framework and opened a HackerOne bounty.

## FAQ

### Was the Fable 5 jailbreak unique to Claude?
No. Anthropic's subsequent investigation, reported in early July, found the same bypass worked on eight frontier models, including OpenAI's GPT-5.5 and Moonshot's Kimi K2.7.

### Why was Claude Fable 5 pulled offline?
Amazon researchers found a jailbreak that got Fable 5 to identify software vulnerabilities and produce demonstration exploit code, triggering the 12 June US export-control order.

### What did Anthropic do to bring its models back?
It trained a new classifier to block the technique, published a draft jailbreak severity framework, and opened a HackerOne bounty for researchers to report cyber jailbreaks.

## Sources

- [How the world's top AI models were revived](https://www.axios.com/2026/07/03/anthropic-ai-models-revived-behind-the-scenes) — Axios, 2026-07-03
- [Anthropic restoring access to its most powerful AI models signals a necessary truce with the U.S. government](https://fortune.com/2026/07/01/anthropic-fable-mythos-ai-models-restored-trump-administration-export-controls/) — Fortune, 2026-07-01
- [Trump restrictions on private AI models turn attention to open source](https://thehill.com/policy/technology/5952253-trump-administration-ai-restrictions-opens/) — The Hill, 2026-06-30