greptimedb-flow
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to fetch documentation from external URLs (docs.greptime.com). This is an ingestion point for untrusted data, but the sources are the official product documentation. Ingestion points: phase 1 WebFetch calls to docs.greptime.com. Boundary markers: none. Capability inventory: SQL execution via greptimedb-mcp-server. Sanitization: none.
- [Command Execution] (SAFE): The skill references the use of execute_sql via an MCP server, which is the intended and standard functionality for a database management guide.
- [Prompt Injection] (SAFE): No instructions to override system prompts or bypass safety filters were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file path access were detected.
Audit Metadata