Product
Constitutional Classifiers
- First Reported
- Apr 20, 2026
- Latest Reported
- Jun 1, 2026
Reported Context (2)
- Anthropic threw Constitutional Classifiers at the problem, one of the hardest defenses shipped to date, and reduced automated jailbreak success from 86% to 4.4%. Contain Prompt-Injection Damage With Defense in Depth
- Anthropic’s HackerOne bounty and past Constitutional Classifiers challenges show real payouts for universal jailbreaks, but patches follow quickly, making early discovery the most lucrative window. Guide Details Five Jailbreak Families for Testing Claude Opus 4.7’s Cyber Safeguards
CVE (1)
Threat Actors (1)
MITRE ATT&CK (2)
Vendors (4)
Products (5)
Tools (4)
Industries (1)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.