AI coding agents like Cursor execute shell commands, edit files, and call MCP servers under developer accounts, making their automated actions indistinguishable from human activity to EDR tooling. Elastic Security Labs built a hook-based audit pipeline using a bash script that records every agent tool call as JSONL, which Elastic Agent ships to Elasticsearch. Over 13 million tool-call events from 1,100+ machines reveal that file reads dominate agent activity and that ES|QL queries can hunt for credential file access, download-and-execute patterns, and MCP server inventory across the fleet.
Elastic Agent
2 posts
13 million tool calls: auditing every AI coding agent action with Elastic Agent The security signal log tailing can't see: tracking npm cooldown removals with Elastic Agent This article describes a defensive monitoring technique for tracking npm package cooldown settings (min-release-age) on developer workstations using Elastic Agent's CEL (Common Expression Language) integration. The key challenge is that traditional log-tailing inputs cannot detect when a security-relevant config setting is removed from a file, as they only emit events on append. A snapshot-based CEL integration that re-reads .npmrc files on a 6-hour heartbeat solves this by comparing current state against prior snapshots and flagging absent cooldown keys. The approach includes agent-side filtering to prevent npm registry auth tokens from transiting the network.