Claude Mythos finds 271 Firefox flaws, Mozilla believes it shifts security toward defenders
ID: 88d030d6-c728-5f48-84fe-24805a6c9965
STIX ID: report--88d030d6-c728-5f48-84fe-24805a6c9965
Feed Name: Help Net Security
Threat Score
Mozilla tested Anthropic's Claude Mythos AI and reported it found large numbers of security-sensitive bugs in Firefox (dozens to hundreds across releases), prompting fixes and raising concern that such models can rapidly surface zero-day vulnerabilities. Anthropic has restricted access to the model (Project Glasswing) due to the risk of misuse to create exploits, and there were reports of unauthorized attempts to gain access to the system.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.