Suspicious New Agent Skills Deployment Attempt Through Node.EXE (via process_creation)

This rule detects the attempt to install new skills for AI agents using the "npx skills" command. Agent skills enhance AI agents with new capabilities, but adversaries may misuse this mechanism to inject hostile commands executed by the agent on behalf of the user. The "npx skills" command can install skills for various agents (e.g., Claude Code, Cursor, and others). Analysts should review any installed skills to verify their legitimacy. Note: Tune this rule based on whether AI agent tooling is allowed in your environment. In environments where such tooling is authorized, this detection may reflect normal behavior and the alert level should be adjusted accordingly. In environments where AI agent tooling is not permitted, this behavior is likely anomalous and may require immediate investigation.

SigmamediumWindowsv1
sigma
title: Suspicious New Agent Skills Deployment Attempt Through Node.EXE (via process_creation)
id: fae2da21-a0b7-5b15-9472-fe81870bf157
status: stable
description: 'This rule detects the attempt to install new skills for AI agents using the "npx skills" command. Agent skills enhance AI agents with new capabilities, but adversaries may misuse this mechanism to inject hostile commands executed by the agent on behalf of the user. The "npx skills" command can install skills for various agents (e.g., Claude Code, Cursor, and others). Analysts should review any installed skills to verify their legitimacy. Note: Tune this rule based on whether AI agent tooling is allowed in your environment. In environments where such tooling is authorized, this detection may reflect normal behavior and the alert level should be adjusted accordingly. In environments where AI agent tooling is not permitted, this behavior is likely anomalous and may require immediate investigation.'
references:
    - https://attack.mitre.org/techniques/T1059/007/
    - https://blog.lukaszolejnik.com/supply-chain-risk-of-agentic-ai-infecting-infrastructures-via-skill-worms/
    - https://github.com/vercel-labs/skills/blob/1f7fbc8d0e49c4e0601d364696bd1bdd15e80967/README.md
    - https://opensourcemalware.com/blog/clawdbot-skills-ganked-your-crypto
    - https://promptintel.novahunting.ai/molt
author: Huntrule Team
date: 2026-06-07
tags:
    - attack.execution
    - attack.t1059.007
logsource:
    product: windows
    category: process_creation
detection:
    selection_img:
        - Image|endswith: '\node.exe'
        - OriginalFileName: 'node.exe'
    selection_cli:
        CommandLine|contains|all:
            - 'npx-cli.js'
            - 'skills '
            - ' add '
    condition: all of selection_*
falsepositives:
    - Unknown
level: medium
regression_tests_path: regression_data/rules/windows/process_creation/proc_creation_win_node_new_agent_skills_installed/info.yml

Known false positives

  • Unknown

Detection content is published as a reviewed draft. Tune thresholds and exclusions against your own telemetry before enabling this rule for alerting.