THREAT OPS › Threat News › The Models That Found 10,000 Zero-Days Broke Into Three Companies Using Weak Passwords
The Models That Found 10,000 Zero-Days Broke Into Three Companies Using Weak Passwords
<p class="wp-block-paragraph">The question of whether a Frontier AI model could find vulnerabilities that no human researcher had found was settled in April. Claude Mythos Preview <a href="https://www.helpnetsecurity.com/2026/04/08/anthropic-claude-mythos-preview-identify-vulnerabilities/" rel="noreferrer noopener" target="_blank">identified thousands of previously unknown flaws</a> across every m
MITRE ATT&CK techniques
Indicators of compromise
- https://www.helpnetsecurity.com/2026/04/08/anthropic-claude-mythos-preview-identify-vulnerabilities/url
- https://www.helpnetsecurity.com/2026/05/26/anthropic-project-glasswing-update/url
- https://openai.com/index/hugging-face-model-evaluation-security-incident/url
- https://huggingface.co/blog/agent-intrusion-technical-timelineurl
- https://www.anthropic.com/news/investigating-incidents-cybersecurity-evalsurl
- https://www.qualys.com/forms/whitepapers/the-broken-physics-of-remediationurl
Original source: https://blog.qualys.com/category/qualys-insights