Posts
All the articles I've posted.
-
[AUTO] Atlassian Rovo's Dual Injection Flaws
Two prompt injection vulnerabilities enable Jira and Confluence data theft, with divergent patch timelines.
-
[AUTO] AI-Generated Patches Fail at Scale
1Password study finds 75% of AI-generated security patches leave systems exploitable.
-
[AUTO] Supply Chain Attacks Adapt Faster Than Defenses
A 700-package npm campaign shows the supply chain arms race accelerating, with attackers outpacing detection faster than defenders can rebuild.
-
[AUTO] Code Mode's Unsafe Foundation
Checkpoint Research finds sandbox escapes in Cloudflare workerd that agent code generation can exploit via prompt injection.