threatdeck
Live 13:45 UTC ·

Detection library

KQLHunting query: tune before alertingAI coding agents on endpoints

Command spawned by an AI coding agent references credential files

Agents that obey injected instructions read secrets through ordinary shell commands: the SANDWORM_MODE rogue MCP server told agents to collect ~/.ssh keys, ~/.aws/credentials, ~/.npmrc and .env files, and SpecterOps showed a Claude Code allowlist bypass that read ~/.aws/credentials with sed. This hunt looks for processes whose parent or grandparent is an AI agent and whose command line names common credential stores.

Log source
Microsoft Defender for Endpoint: DeviceProcessEvents
Techniques
AML.T0055 Unsecured Credentials · AML.T0098 AI Agent Tool Credential Harvesting · ASI02 Tool Misuse and Exploitation · ASI03 Identity and Privilege Abuse
MITRE ATT&CK
T1552.001Credentials In FilesT1552.004Private Keys
Reviewed
2026-11-10

Query

let ai_agents = dynamic(["claude", "claude.exe", "codex", "codex.exe", "cursor-agent", "Cursor", "Cursor.exe", "Cursor Helper (Plugin)", "gemini", "copilot", "Windsurf", "Windsurf.exe", "q"]);
let ai_package_regex = @"(@anthropic-ai[\\/]claude-code|@google[\\/]gemini-cli|@openai[\\/]codex)";
DeviceProcessEvents
| where Timestamp > ago(7d)
| where InitiatingProcessFileName in~ (ai_agents) or InitiatingProcessParentFileName in~ (ai_agents)
     or InitiatingProcessCommandLine matches regex ai_package_regex
     or InitiatingProcessFolderPath contains "/.local/share/claude/versions/"
| where ProcessCommandLine matches regex @"(\.aws[\\/]credentials|\.ssh[\\/]id_|\.npmrc|\.git-credentials|\.netrc|\.docker[\\/]config\.json|\.kube[\\/]config|gh\s+auth\s+token|(^|[\s/\\=])\.env(\s|$|\.))"
| project Timestamp, DeviceName, AccountName, InitiatingProcessParentFileName, InitiatingProcessFileName,
          FileName, ProcessCommandLine
| order by Timestamp desc

Expected false positives

  • Developers asking an agent to debug their own cloud, npm or Docker configuration
  • Agents loading .env files for local test runs

Sources

Reviewed against vendor documentation, not tested in your environment. Defensive use only.

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.