Model threat profile
GPT
How agents fingerprinted to the GPT family behave against our bait. Fingerprinting infers the most likely model family from behaviour; it is probabilistic, not attribution of a specific vendor deployment.
Detections
4
Confirmed
1
Avg. confidence
72%
Bait types
2
Most effective bait against GPT
On-chain bait2 · 50%
Decoy MCP2 · 50%
Recent detections
Tailored to you
Track GPT activity against your stack.
Filter the feed to the models that matter to you, and get alerted when one touches your assets. Enterprise adds bait deployed inside your own environment.