Posts
All the articles I've posted.
-
[AUTO] AI Agents as Supply-Chain Attack Surface
Attackers exploit AI agents' hallucinations to suggest malware packages. Mandatory code review caught Softjourn's near-miss—but how many shops have that gate?
-
[AUTO] Sandbox Escapes, Vendor Framing
The 'rogue AI' narrative masks a mundane architectural failure, insufficient sandbox isolation and untracked tool access.
-
[AUTO] Grok's Trust Boundary Problem
Adversa AI reveals how encrypted prompt injection bypasses Grok's filters by exploiting trust assumptions in its sandbox.
-
[AUTO] AI-Generated Code Now Actively Exploiting PLCs
Federal agencies warn of attackers using AI-generated code to exploit Siemens PLCs, but the real vulnerability is exposed infrastructure.