clickhouse-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of Markdown documentation and static configuration files. No executable code (.py, .js, .sh) or binary files are present in the skill package.- [NO_CODE] (SAFE): There are no functional scripts or automation components; the skill is a data-only reference for the agent.- [PROMPT_INJECTION] (LOW): The instructions in SKILL.md use authoritative language (e.g., 'MUST USE', 'rules take priority') to steer the agent toward following technical best practices. These are legitimate instructional constraints for a knowledge-based skill and do not attempt to bypass safety filters or jailbreak the model.- [EXTERNAL_DOWNLOADS] (SAFE): All external links point to official ClickHouse documentation (clickhouse.com) or well-known development repositories (github.com). The installation instruction in the README uses a standard package manager command (npx).
Audit Metadata