clickhouse-sdk-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard implementation patterns for the ClickHouse Node.js client. It follows security best practices by using environment variables for sensitive credentials (
CLICKHOUSE_HOST,CLICKHOUSE_USER,CLICKHOUSE_PASSWORD) rather than hardcoding them. - [INDIRECT_PROMPT_INJECTION]: The skill implements a data ingestion surface by facilitating database queries (
client.query) and inserts (client.insert). - Ingestion points: Data enters the agent's context through query results in
SKILL.mdandreferences/implementation.md. - Boundary markers: The instructions explicitly advise using typed parameters (
{name:Type}) to prevent SQL injection at the database layer. - Capability inventory: The patterns include database read and write operations across
SKILL.mdandreferences/implementation.md. - Sanitization: SQL parameterization is recommended as a core pattern to ensure data integrity during database operations.
Audit Metadata