Skip to main content
Lab Verified: 2026-11-16

Adversary AI Agent Cloud Token Abuse via STS

Autonomous AI agents exploit CVE-2026-42271 and CVE-2026-48710 in LiteLLM and Dify to steal cloud API keys. Implement Starlette patches and hunt STS pivots.

CloudAppEvents
| where Timestamp >= ago(7d)
| where ActionType in~ ("GetCallerIdentity", "AssumeRole", "CreateAccessKey")
| summarize CallCount = count() by AccountName, tostring(IPAddress), bin(Timestamp, 1h)
| where CallCount > 10
Need to defang indicators or test triage logs?
Use our zero-telemetry client-side parser to extract, defang & format indicators.
Open SOC Defanger Workbench
Target Log Sources & Tables
CloudAppEvents

Ensure telemetry connector is actively ingesting this table into your Sentinel workspace or Defender XDR.

False Positives & Tuning Guidance

Authorized continuous deployment pipelines executing STS roles.

Source Incident Analysis

Autonomous AI Agents: How to Detect LiteLLM & Dify Exploits

Disclosed: 2026-11-16

Read Attack Chain
DETECTION_ENGINEERING_FEEDBACK

Have tuning recommendations, encounter false positives in your environment, or want to contribute rule improvements?

Submit Feedback →