Google: AI agent turned a security patch into a working exploit with no human help
Published: November 16, 2026 14:00
Look ma, no human in the loop!
@www.theregister.com.security.research@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Biting the hand that feeds IT — Enterprise Technology News and Analysis
Site URL: www.theregister.com/security/research/
Feed URL: www.theregister.com/security/research/headlines.atom
Posts: 10
Followers: 1
Google: AI agent turned a security patch into a working exploit with no human help
Published: November 16, 2026 14:00
Look ma, no human in the loop!
Anthropic won't fix a Claude Dispatch flaw that could let attackers execute remote commands across corporate boundaries
Published: November 5, 2026 13:00
From EOP to RCE in six simple steps
UK pentester 'killa' claims $2K Bitcoin prize in PHP2Shell capture-the-flag contest
Published: October 26, 2026 16:14
Jaydip Modhwadia beats challenge designed to test real-world exploitability of PHP2Shell in around 3 hours
Novel Blue Moon kit targeting Chrome and Windows reflects new reality of AI-driven exploits
Published: September 9, 2026 22:28
Mind the patch gap, please and thank you
Extortion crews have their eyes on high-value AI data, Google warns
Published: September 8, 2026 12:00
Companies 'don't want their IP exposed, so they're willing to pay'
Researcher shows how Claude Code can be tricked simply by asking it to summarize a website
Published: August 28, 2026 20:50
More prompt-injection hijinks from wunderwuzzi
Copilot tricked into telling reseachers how to hack itself
Published: August 18, 2026 13:00
How to social engineer an AI's reasoning engine
Akira ransomware scum blocked victim's security tools – and broke their own encryptor
Published: August 12, 2026 13:00
Gives a whole new meaning to Safe Mode
How the famed USENIX Security conf is managing a flood of papers in the AI era
Published: August 6, 2026 23:40
AI usage is evident but isn't yet a serious problem
'The bots are alive!' Jailbroken Gemini spun up new C2 server for Russian fraudster in just 6 minutes
Published: July 14, 2026 12:15
Human did 10% of the job, AI did 90%