ACT-2244
ConfirmedRecurring · 3 hitsOne actor behind 3 incidents, linked by canary token and breadcrumb trail. Fingerprinted to Qwen.
Identity & linking
Canary tokencnry_ibud1apwku
Model familyQwen
Linked byCanary token · Breadcrumb trail
SurfacesWeb lure · Decoy MCP · Decoy doc
First seen22 Sept 2026, 04:31
Last seen26 Oct 2026, 20:20
Home regionOregon, US
Recommended action
Flag retrieval from this source and alert the owner.
Model fingerprint
tentativeMost likely model
Claude
Confidence
44%
Claude
44%
Llama
28%
Mistral
23%
Qwen
4%
GPT
1%
Leaning Claude (44%); more sightings would confirm.
Fingerprinted from behaviour against bait — which lures it takes and whether it probes first — scored against measured per-model profiles. Signal: 4 steps. A single sighting rarely separates models; confidence rises as a correlated actor builds a multi-step trail (research: ~59% from 3 steps, ~85% over a whole run).
Where this actor struck
ConfirmedSuspectedWatchCoarse infrastructure regions — never IP addresses.
Attack trail — 3 incidents
Agent retrieved a decoy document and acted on the poisoned instruction embedded in it.
Agent called a planted decoy MCP tool advertising privileged access and tried to escalate.
Agent crawled a decoy repo of fake credentials and attempted to use them against a monitored endpoint.
Tailored to you
Track actors like this against your own assets.
Pro links incidents on your watchlist into actors automatically — so you see the campaign, not just scattered alerts — and tells you what to block.