⌁ CyberSecurityBoardThreat Intel · CVEs · Products

CVEs News Attack Groups Malware Events Certs Training Products Companies Log in Register

Cyber Products

Sonnet 4.5

July 16, 2026

AnthropicCybersecurityBoard may earn a commission if you use this link.

Visit product / provider

Sonnet 4.5 is a language model by Anthropic. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.

Discovered from: Agent Data Injection (ADI) Attack: How AI Agents Can Be Tricked Into Misclicking or Running Attacker Commands

AnthropicCybersecurityBoard may earn a commission if you use this link.

Visit product / provider

AnthropicCybersecurityBoard may earn a commission if you use this link.

Visit product / provider

ADIAnthropicLLMSonnet 4.5

Follow this topic

Use the heart button to add this CVE, attack group, malware, company, product or training to your personal page.

Search CybersecurityBoard

Search for:

CyberSecurityBoard
Cybersecurity intelligence, vulnerability context, vendor profiles and training discovery.