clickhouse
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs all actions, including authentication and data retrieval, by executing the
@useclawlink/clitool via the command line. - [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to run
npx @useclawlink/cli, which downloads the necessary package from the official NPM registry at runtime. These resources belong to the skill's official vendor infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary data retrieved from ClickHouse databases, creating a vector where untrusted data could influence agent behavior.
- Ingestion points: Results from
clickhouse_execute_queryand schema metadata from table inspection actions (SKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the database output.
- Capability inventory: The skill possesses the capability to execute shell commands and interact with external database services through the CLI tool.
- Sanitization: There is no evidence of filtering, escaping, or validation of the content returned from ClickHouse before it is presented to the agent's context.
Audit Metadata