Dragos: AI prompts leak planted secrets
Trackable secrets test · three providers breached
14 stories about Security in AI coding from AI Coding News, newest first. All topics
Trackable secrets test · three providers breached
Attackers used the open-source tool Cairn
A synthetic internet for prompt-injection tests
Reuters cites internal posts; Meta has not responded
Politico's sources point to the ARTEX AI tool
Poisoned agent-framework versions stole credentials
Adaptive effort · secret detection · public preview
F5 patches HTTP/2 code-execution bugs · found by five teams
Agent Framework 1.26.1 and 1.26.2 · credential stealer · now quarantined
CVE-2026-114938 · Oracle has released a patch
High- and critical-severity bugs · from January 1, 2027
FBI advisory, Friday, Nov 13 · ConnectWise customers, South Korean banks
Google Threat Intelligence Group · first with no human in the loop
One of at least nine AI platform breaches in October