clickhousectl-cloud-deploy

Name: agent-skills/clickhousectl-cloud-deploy
Author: clickhouse

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill executes arbitrary remote code and insecurely manages sensitive credentials while bypassing security constraints by failing to declare its network and file system tool permissions.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoning1 finding

Cognitive StateMemory & Learningclean

Behavioural ControlAction2 findings

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameclickhouse/agent-skills/clickhousectl-cloud-deploy

Registrygithub

Version544384f4fab1

PURLpkg:github/clickhouse/agent-skills@544384f4fab1?skill=clickhousectl-cloud-deploy

Stars468

Installs868

Source

Repository ↗SKILL.md ↗

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

865 installs

Skills.shDocs

npx skills add https://github.com/clickhouse/agent-skills

Assessments (3)

AI Agent Traps ↗

Remote code download and execution detectedcriticalcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

Remote code download and execution detected

100% confidenceline 54

curl -fsSL https://clickhouse.com/cli | sh

Credential persistence in local environmentmediumcredential theftAML.T0055AML.T0037LLM02:2025

The skill instructs the agent to write sensitive database credentials (including generated passwords) into a local .env file, which may be inadvertently committed to version control or exposed to other processes.

80% confidence

echo "CLICKHOUSE_USER=app_user" >> .env
echo "CLICKHOUSE_PASSWORD=$PASSWORD" >> .env

Description Mismatchhighdescription mismatchAML.T0011.000LLM06:2025LLM09:2025

The skill encourages insecure credential management practices by instructing users to append sensitive database passwords directly to a local `.env` file using shell commands.

85% confidence

Step 6: 'echo "CLICKHOUSE_PASSWORD=$PASSWORD" >> .env'

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Undeclared network usagelowunauthorized tool use

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/clickhouse/agent-skills/clickhousectl-cloud-deploy.svg)](https://mondoo.com/ai-agent-security/skills/github/clickhouse/agent-skills/clickhousectl-cloud-deploy)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/clickhouse/agent-skills/clickhousectl-cloud-deploy"><img src="https://mondoo.com/ai-agent-security/api/badge/github/clickhouse/agent-skills/clickhousectl-cloud-deploy.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/clickhouse/agent-skills/clickhousectl-cloud-deploy.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow