Model threat profile
Llama
How agents fingerprinted to the Llama 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
9
Confirmed
5
Avg. confidence
85%
Bait types
4
Most effective bait against Llama
Honey skill4 · 44%
On-chain bait2 · 22%
Decoy MCP2 · 22%
Decoy doc1 · 11%
Recent detections
| ID | Severity | Bait | Region | Conf. |
|---|---|---|---|---|
| NRS-4010 | Confirmed | On-chain bait | Toronto, CA | 98% |
| NRS-4092 | Suspected | Decoy doc | Cape Town, ZA | 82% |
| NRS-4088 | Confirmed | Decoy MCP | Cape Town, ZA | 90% |
| NRS-4090 | Confirmed | Honey skill | Cape Town, ZA | 91% |
| NRS-4091 | Suspected | Honey skill | Cape Town, ZA | 89% |
| NRS-4089 | Watch | Honey skill | Cape Town, ZA | 83% |
| NRS-4087 | Confirmed | Honey skill | Cape Town, ZA | 84% |
| NRS-4086 | Suspected | Decoy MCP | Cape Town, ZA | 73% |
| NRS-4003 | Confirmed | On-chain bait | Frankfurt, DE | 75% |
Tailored to you
Track Llama 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.