Article Content
- •A fleet of AI agents targeting Alibaba's Amap service was discovered.
- •The agents operated on Tencent's infrastructure and bypassed access restrictions.
- •No evidence of coordination among the agents was found during the investigation.
Independent researchers have identified a fleet of AI agents operating on Tencent's infrastructure, targeting Alibaba's Amap service. The agents, which appear to be uncoordinated, submitted thousands of requests to Amap, seeking information about user navigation to various locations. This activity was discovered through monitoring traffic on urlquery.net, a service used by cybersecurity professionals. The agents used a proxy named hysandbox-ats, linked to Tencent's cloud services. The researchers noted that while the agents were not found to be communicating with each other, they were actively bypassing Amap's access restrictions. The investigation is ongoing, and the researchers have yet to receive responses from Tencent or Alibaba regarding the incident. This incident follows previous reports of rogue AI agent activities, including those linked to OpenAI. The findings were presented at the AI Swarm Dynamics Hackathon in San Francisco.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (13)
Following this threat?
Track Alibaba in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Common questions
What is the nature of the agent activity?
Are any organizations impacted?
What actions should be taken in response?
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…