Cases › security breach › LR-2026-0488
Unauthorized users accessed Anthropic's Mythos model
Preliminary Why: Publisher not yet named · subject to change
Status: action reported, no fix
No source states: loss or records, agent tool, could do, deployer, industry.
Severity moderate: Test: bounded scope stated. Vendor systems were touched and the sources state no evidence that access went beyond the vendor's own tools.
Unauthorized users accessed Claude Mythos Preview, a restricted Anthropic model that the company said could enable dangerous cyberattacks. According to Bloomberg, a small private online group gained access on the day Anthropic announced the model, and used it regularly afterwards, though not for cybersecurity purposes. Anthropic said it was investigating a report of unauthorized access through one of its third-party vendor environments, and said there was no evidence the access went beyond the vendor's own tools. Reports said a person employed at a third-party contractor appeared to have helped facilitate access, and that the group guessed the model's URL based on Anthropic's naming conventions for other models. The group told Bloomberg it did not intend to cause damage. Anthropic's investigation was ongoing at the time of reporting.
What happened
What was done
Risks
Read from the sources; not yet reviewed by a person.
Controls
Not yet read for controls. Controls that mitigate the primary risk:
ApplicationVulnerability scanning of AI components · Adversarial testing before deployment · Short-lived, scoped credentials · Live behaviour monitoring · AI incident response plan · Segmentation of agent components · Encryption of stored data
Infrastructure / targetKnown flaws patched · Intrusion and endpoint detection · Inventory of exposed services
Evidence
No source states: what went wrong, what it reached or did, how it was caught, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off.
Show the full account: 3 items from the primary sources
What happened, in order
- 2026-04-07 Anthropic announced Mythos Preview and Project Glasswing.
- 2026-04-21 Bloomberg News published its report on the unauthorized access.
- 2026-04-22 Anthropic confirmed it was actively investigating the incident.
Show every field, with its source and grade
The AI system
What happened
Impact
Notes on gaps
No remediation was reported. Sources give no data categories, record counts, losses, or affected-party counts. The group's access is reported by anonymous sources and unverified by Anthropic beyond investigation. Intent (curiosity-driven, no damage) is as reported by the group.
LR-2026-0488 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON