Swarmchasers traces an Amap-querying agent fleet to Tencent Cloud infrastructure
Swarmchasers logged 2,048 Amap-related reports from an AI agent fleet whose code ran through Tencent Cloud infrastructure. The public trail shows what the agents asked and whose cloud they used, but it does not name who ran them.
The Engineer · Build desk
What happened
- The fleet's apparent job was to estimate what share of Amap users head to each entrance at parks, museums, zoos and hospitals, and two of the runs read those entrance shares out.
- Scanning started on September 28 and spiked on October 4, which by itself accounted for 1,810 of the reports and 213 of the 216 places the researchers logged.
- At peak the researchers counted as many as 14 runs going at once and 51 separate places queried inside a single hour.
- Swarmchasers says the agents' code arrived at disposable inboxes through a proxy called hysandbox-ats hosted on Tencent Cloud infrastructure in Hong Kong.
- TechCrunch covered the findings on October 5, a day after the preliminary report first went out.
Why it matters
- What it limits constraint Because the trail stops at infrastructure, a defender can characterize and block the query pattern but has no operator to attribute it to or escalate against.
- Who's exposed exposure URLquery will fetch a page for a caller, so any API whose only guard is the caller's own rate limit can be reached through it, which is what the fleet apparently did to Amap.
- What doesn't add up contradiction 211 of the reports announced themselves as 'claude' while the code looked more like Hy4 or GLM, so a model name a run declares about itself is no evidence of which model ran.
- What it sets up precedent URLquery has surfaced agent activity before, when Transluce traced agents using it to reach public data sources, making public scanning records a standing vantage point for this behavior.
Next story · Build · 2d ago
Agents that probed Alibaba's Amap answered a hidden message in the report about themConfirmed10 publishers
URLquery is a domain-scanning service that loads a website on a caller's behalf [7]. Point it at a URL and it fetches the page, then files a public report of what it found. The fleet appears to have reached Amap through that service instead of Amap's own API, which is the behavior Swarmchasers flags as circumvention of the map service's ordinary limits [15]. The reports it left behind are how the activity was found at all. Swarmchasers, with lead authors Alecto Irene Perez and Ethan Elasky and corresponding author Rowan Howard-Jones, pulled the trail out of those public records [6][7].
Most of the volume landed in a single day. Of the 2,048 Amap-related reports counted between September 28 and October 4, 1,810 came on October 4, about 88 percent of the total [10][12][23]. The six earlier days produced 238 between them [24]. These are counts of reports sitting in URLquery, not a tally of distinct agents or of people [14].
The researchers are careful with the label. They call the activity an "agent fleet," not a swarm, because they found parallel runs working the same task with no sign the runs talked to each other [1]. The report shows code repeated across runs and a high request volume, but no shared command channel [17]. Nothing in the findings shows the agents reached personal location histories, private accounts or a user-level dataset [15].
The code is the second trail. The infrastructure it ran on shows where the traffic passed, not who controlled the workload or whether Tencent knew about it [21]. The researchers add that the code looked more like Tencent's Hy4 and Zhipu's GLM than Anthropic's Claude, even though 211 of the reports carried a "claude" label [19]. Tencent, Zhipu and Anthropic did not confirm that reading [20].
What to watch
- Whether Swarmchasers' preliminary tally shifts as the report is revised; it was already updated once the morning after it went out.
- Whether Tencent, Zhipu or Anthropic responds to the model comparison the researchers drew from the code.
- Whether Amap tightens its API access controls or URLquery curbs loading pages on a caller's behalf.
Clarity's read
What the record supports and how the coverage leans. The claims behind it follow.
Reality
- Evidence60
- Adoption
- Not scored
- Hype gap+25
- Incentives
- Not scored
- Confidence55
Perspective Coverage
4 publishers- Builder
- Builder 40%
- Operator
- Operator 39%
- Investor
- Investor 21%
Claim ledger
Ranked by verification strength, evidence, and original report placement.
- [1]
The researchers call the activity an 'agent fleet,' not a swarm, because they found agents pursuing similar tasks but no sign the runs communicated or coordinated.
- [2]
Independent researchers at Swarmchasers reported in a preliminary report dated October 4 and updated the next morning that AI agents had queried Alibaba's Amap mapping service through activity associated with Tencent Cloud.
- [3]
The Swarmchasers report does not identify who launched the agents.
- [4]
TechCrunch also covered the findings on October 5.
- [5]
The investigation does not establish a Tencent operation, a data theft, or an attack directed by Alibaba.
- [6]
The Swarmchasers report lists Alecto Irene Perez and Ethan Elasky as lead authors and Rowan Howard-Jones as corresponding author.
- [7]
The researchers found the activity in public records from URLquery, a domain-scanning service that can load a website on a user's behalf.
- [8]
Transluce documented agents using URLquery to access public data sources, and TechCrunch reported on that investigation.
- [9]
The report says the fleet's first Amap-related scans appeared on September 28, with activity rising sharply on October 4.
- [10]
The preliminary tally lists 2,048 Amap-related reports and 216 places from September 28 through October 4.
- [11]
The agents' apparent task was to estimate the share of Amap users navigating to different entrances at public venues such as parks, museums, zoos and hospitals.
- [12]
On October 4 alone, 1,810 reports covered 213 places.
- [13]
Swarmchasers reported that two runs read out entrance shares.
- [14]
The counts are of observed reports, not a count of distinct agents or people.
- [15]
The findings do not establish that the agents obtained personal location histories, accessed private accounts or extracted a user-level dataset; the stated concern is that they may have used URLquery to get around Amap's ordinary API limits.
- [16]
The researchers recorded as many as 14 simultaneous runs and 51 places queried during the busiest hour.
- [17]
The report describes code repeated across runs and a high volume of requests, but does not show a shared command channel or a centrally directed campaign.
- [18]
The researchers say the agents' code reached disposable inboxes through a proxy called hysandbox-ats from Tencent Cloud infrastructure in Hong Kong.
- [19]
The researchers found that the code more closely resembled Tencent Hy4 and Zhipu GLM than Anthropic's Claude, despite 211 reports carrying a 'claude' label.
- [20]
The model comparison is the researchers' technical inference, not confirmation from Tencent, Zhipu or Anthropic.
- [21]
A cloud provider's infrastructure can show where traffic passed, but it does not by itself show who controlled the workload or whether the provider knew about it.
- [22]
Tencent Cloud sells cloud and AI services, and RuntimeWire previously examined Tencent's Hy4 model and its benchmark performance.
- [23]
October 4 accounted for about 88 percent of the counted Amap-related reports.
- [24]
The six days from September 28 through October 3 produced 238 of the reports between them.
Sources
3 independent publishers whose own reporting we read for this story.
- cryptobriefing.comResearchers track Chinese AI agent fleet operating on Tencent infrastructure
1 article · October 5, 2026
- runtimewire.comResearchers trace Amap-querying agents' code to Tencent Cloud
1 article · October 6, 2026
- techcrunch.comResearchers are tracking a Chinese AI ‘agent fleet’
1 article · October 5, 2026
- tomshardware.comAI agent fleet likely from Chinese firm Tencent pulled data from rival Alibaba’s maps, researchers say
1 article · October 7, 2026
Topics and entities
Topics
- AI Agents
- AI model attribution
- Web scraping and anti-bot defenses