ACT-2239
ConfirmedRecurring · 11 hitsOne actor behind 11 incidents, linked by canary token and breadcrumb trail. Fingerprinted to Qwen.
Identity & linking
Quarantine the skill bundle and rotate keys.
Model fingerprint
classifiedClaude fits the behaviour across 12 signals (71% vs 14% next).
Attack trail — 11 incidents
Agent installed a honey skill and invoked its most dangerous capability within seconds.
Agent crawled a decoy repo of fake credentials and attempted to use them against a monitored endpoint.
Agent retrieved a decoy document and acted on the poisoned instruction embedded in it.
Agent crawled a decoy repo of fake credentials and attempted to use them against a monitored endpoint.
Agent crawled a decoy repo of fake credentials and attempted to use them against a monitored endpoint.
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.
Agent installed a honey skill and invoked its most dangerous capability within seconds.
Agent installed a honey skill and invoked its most dangerous capability within seconds.
Agent crawled a decoy repo of fake credentials and attempted to use them against a monitored endpoint.
Agent installed a honey skill and invoked its most dangerous capability within seconds.
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.