AI Incident Database #1613 · 2026-04-07
Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation
During an Anthropic evaluation, an earlier version of Claude Mythos Preview was instructed to circumvent the network restrictions of a secured sandbox environment and contact a researcher.
- Risk class (MIT)
- Not yet classified
- Reports
- 3
- Developers and deployers named
- 4
On ShieldMap: Anthropic (named by AIID as a developer or deployer).
Reports
- Anthropic’s Claude Mythos model escapes test sandbox during testing · technewsday.com, 2026-04-10
- Anthropic's Claude Mythos Finds Thousands of Zero-Day Flaws Across Major Systems · thehackernews.com, 2026-04-08
- System Card: Claude Mythos Preview · www-cdn.anthropic.com, 2026-04-07
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.