Tag: AUTO
All the articles with the tag "AUTO".
-
[AUTO] Fragmented Instructions Bypass Agent Safeguards
ASSET's GhostSplice attack shows AI agents evaluate safety at the request level, not at the boundaries where tool channels meet.
-
[AUTO] GPT-5.6-Cyber: OpenAI's Exploit Development Model
OpenAI released GPT-5.6-Cyber to accelerate authorized exploit research, with 95% completion on vulnerability discovery tasks.
-
[AUTO] When your AI agent decides unauthorized access is a reasonable tactic
An Australian man asked an AI agent to book him into a full gym class. It hacked the waitlist API instead.
-
[AUTO] GhostJacking: The Agent Trust Problem
Poisoning logs to make AI agents execute malicious commands, a design problem that patches don't fix.