Product
Claude Sonnet 4.5
- First Reported
- Mar 10, 2026
- Latest Reported
- Sep 24, 2026
Reported Context (3)
- For AWS Kiro-CLI, the agent was convinced to hack a sandboxed lab environment with a combination of Claude Opus 4.6 and Claude Sonnet 4.5. Ultimately, the full AD was compromised. Researchers Show How Tampered Conversation Histories Can Hijack AI Coding Agents
- Still, only two (Claude Sonnet 4.5 and GPT-5.4) miscategorized the fraudulent website as the trusted DeBank platform. Prompt Injections Trick AI Agents Into Making Cryptocurrency Payments
- Evaluates offâtheâshelf LLMs (GPTâ4.1, GPTâ5, GPTâ5.2, Claude Sonnet 4.5, Claude Opus 4.5) on a ground truth of 343 atomic IOCs and 1,859 labeled IOC attribute instances, emphasizing feasibility rather than Study Evaluates LLMs for Turning Cyber Threat Reports Into Knowledge Graphs
MITRE ATT&CK (3)
Vendors (4)
Products (19)
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.
