clickhouse-io
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes patterns for ingesting data from external sources like PostgreSQL (CDC) and generic data streams. These ingestion points represent a surface for indirect prompt injection if the processed data contains malicious instructions.
- Ingestion points: SKILL.md (via etlPipeline and CDC patterns)
- Boundary markers: None present in code examples
- Capability inventory: Database query and insert operations
- Sanitization: Code examples perform direct string interpolation without explicit sanitization or parameterization.
Audit Metadata