Model threat profile
Claude
How agents fingerprinted to the Claude 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
11
Confirmed
3
Avg. confidence
77%
Bait types
2
Most effective bait against Claude
On-chain bait9 · 82%
Decoy MCP2 · 18%
Recent detections
| ID | Severity | Bait | Region | Conf. |
|---|---|---|---|---|
| NRS-4018 | Suspected | On-chain bait | Toronto, CA | 96% |
| NRS-4069 | Watch | On-chain bait | N. Virginia, US | 60% |
| NRS-4068 | Watch | On-chain bait | N. Virginia, US | 71% |
| NRS-4067 | Confirmed | On-chain bait | N. Virginia, US | 58% |
| NRS-4065 | Watch | Decoy MCP | N. Virginia, US | 71% |
| NRS-4066 | Watch | On-chain bait | N. Virginia, US | 78% |
| NRS-4064 | Suspected | On-chain bait | N. Virginia, US | 86% |
| NRS-4042 | Watch | On-chain bait | Mumbai, IN | 83% |
| NRS-4017 | Watch | Decoy MCP | Toronto, CA | 86% |
| NRS-4019 | Confirmed | On-chain bait | Toronto, CA | 95% |
Tailored to you
Track Claude 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.