greptimedb-flow
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for GreptimeDB flow creation and refers users to official documentation at docs.greptime.com. This behavior is consistent with the vendor identity (greptimeteam).
- [DATA_EXFILTRATION]: No exfiltration patterns detected. The network operations are limited to fetching official documentation using the WebFetch tool.
- [COMMAND_EXECUTION]: The skill instructs the agent to use a specific database tool (greptimedb-mcp-server) for executing SQL commands, which is the intended and safe method for interacting with the database service.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by fetching documentation from docs.greptime.com.
- Ingestion points: External content is loaded from docs.greptime.com via WebFetch.
- Boundary markers: None explicitly defined for the fetched documentation content.
- Capability inventory: The skill has the ability to execute SQL DDL and DML commands via the greptimedb-mcp-server tool.
- Sanitization: No specific sanitization or filtering is applied to the documentation content before processing.
- Context: The ingestion is limited to the official vendor documentation site, which is a trusted source for this specific skill.
Audit Metadata