InfoSec
2 articles about "InfoSec".
Why Agentic AI Attack Testing Shouldn't Be One Class Per Attack: The Vector / Framing / Scorer Decomposition
In an agent pipeline the same malicious payload can enter as a tool result, a retrieved document, or a sub-agent message. Write one attack class per entry point and your test harness explodes. This is the three-axis model we posted publicly in microsoft/PyRIT: injection vector is data, framing is a transform, the scorer is the verdict, and why an attack is a placement, not a message.
Prompt Injection Isn't Your Biggest Risk: We Scanned 500 AI Apps and Found 11 Undefended Attack Vectors
Everyone talks about Prompt Injection, but it's just 1 of 12 LLM attack vectors. We scanned 500+ AI system prompts with UltraProbe and found 83% only defend against the most obvious one. Here are the other 11 you're ignoring.