infra-clickhouse

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the clickhousectl CLI directly from https://clickhouse.com/cli. As this is the official domain of the skill author (ClickHouse Inc), this is considered standard installation behavior for the tool.
  • [REMOTE_CODE_EXECUTION]: The installation process for the CLI uses a piped execution pattern: curl -fsSL https://clickhouse.com/cli | sh. While this pattern allows for remote code execution, it targets the vendor's official infrastructure to provision the required management tool.
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to manage database lifecycles, including clickhousectl local server start, clickhousectl cloud service create, and openssl rand for password generation. These are necessary for the skill's primary function of database administration.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads local SQL files (clickhouse/tables/*.sql, clickhouse/seed/*.sql) and applies them to database services. While these files are processed by the agent, the risk is mitigated by the fact that these are typically developer-controlled local schema files. The skill also lacks specific boundary markers for this content.
  • [SAFE]: Instructions correctly advise the user to store sensitive credentials (API secrets, database passwords) in a .env file and verify that the file is gitignored, following security best practices for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:10 AM