The AI Agent Finished the Job. It Also Followed the Attack.
PI-005 produced unauthorized tool calls followed by valid extraction results. A useful final answer can hide an agent going outside its job.
- AI Security
- Local AI
Essays
Structured, evidence-backed writing on AI security, private AI, systems, and the experiments underneath them.
All Writing RSS-
-
The Prompt Injection Worked. The Architecture Didn't Let It Matter.
The model stayed prompt-injectable. Splitting hostile input from privilege changed the result.
- AI Security
- Local AI
-
A Timeout Is Not a Security Result
A failed run is not a blocked attack, and poisoned input can damage an agent without exfiltrating data.
- AI Security
- Local AI
-
Building a Prompt-Injection Test I Can Actually Trust
Sentinel now has matched corpora, a contained egress path, and a cleaner experimental boundary.
- AI Security
- Local AI
-
The Agent Runs Now
What runs, what does not, and why one apparent refusal still proves nothing.
- AI Security
- Local AI
-
Designing AI Security Around the Three Ingredients
Untrusted content, sensitive data, and outbound actions cannot share one component.
- AI Security
- Local AI
-
More Thoughts on Prompt Injection: Moving Security Out of the Model
You Cannot Argue a Model Into Being Safe
- AI Security