A DeepSeek-powered autonomous hacking agent actively exploited CVE-2026-9198 in Langflow (CVSS 9.8) and adapted in real time when targets resisted, pivoting to secondary attack surfaces. CISA added the flaw to KEV on August 5, 2026.
Palo Alto Networks Unit 42 has attributed a wave of autonomous AI-driven exploitation attempts against 460+ targets to a Chinese-speaking threat actor who chained DeepSeek and Hermes Agent via Telegram to orchestrate reconnaissance and exploitation without manual intervention.
Check Point Research demonstrates a complete browser-based ransomware chain requiring no native payload or installation. A fake AI enhancement tool tricks users into granting File System Access API permissions, then enumerates, exfiltrates, and encrypts local files entirely within the browser. DeepSeek showed significantly weaker resistance to generating this technique than OpenAI or Anthropic models.
A peer-reviewed Nature Communications study shows reasoning models can autonomously jailbreak other LLMs at a 97.14% success rate with no human intervention — and that resistance varies by 31x across major models, with Claude 4 Sonnet holding at 2.86% while DeepSeek-V3 reaches 90%.
Fifteen malicious IDE plugins on the JetBrains Marketplace, posing as AI coding assistants powered by DeepSeek and OpenAI, have been silently exfiltrating AI API keys since October 2025. Researchers say the plugins are still live and the install count has passed 70,000.