Google: AI agent turned a security patch into a exploit with no human help
sshah03
12 points
3 comments
November 16, 2026
Related Discussions
Found 5 related stories in 196.5ms across 13,334 title embeddings via pgvector HNSW
- Google: Attackers are using prompt injection against coding agents fourfire · 11 pts · September 09, 2026 · 67% similar
- AI-found bugs aren't proving any easier to exploit despite the hype sbulaev · 14 pts · July 28, 2026 · 64% similar
- AI-found bugs aren't proving any easier to exploit despite the hype Tomte · 14 pts · July 29, 2026 · 64% similar
- OpenAI agents hijacked German website in previously undisclosed AI breakout negura · 93 pts · September 04, 2026 · 62% similar
- Google's Gemini AI hacked three companies in security test luxpir · 26 pts · September 19, 2026 · 62% similar
Discussion Highlights (2 comments)
sshah03
Also relevant: https://cloud.google.com/blog/topics/threat-intelligence/age...
serk_official
I was just thinking about this last night! What is the future of security if AI was used in tandem with exploits and fooling even other AI models. What a crazy time to live in!