clickhouse
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx @useclawlink/cli, which downloads and executes the vendor's command-line tool directly from the NPM registry. - [COMMAND_EXECUTION]: All primary functions, including authentication, service connection, and SQL query execution, are performed by running shell commands via the ClawLink CLI.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data and metadata retrieved from ClickHouse databases.
- Ingestion points: SQL query outputs and schema definitions retrieved from ClickHouse using the
runanddescribeactions inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the retrieved database content.
- Capability inventory: The skill allows for shell command execution (
npx) and database read operations across various tables and schemas. - Sanitization: There is no mention of sanitization or validation of the data retrieved from ClickHouse before it is processed by the agent.
Audit Metadata