skills/agentskillexchange/skills/Anyquery Universal SQL Engine with MCP Integration/Gen Agent Trust Hub
Anyquery Universal SQL Engine with MCP Integration
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions.
- [PROMPT_INJECTION]: The skill allows querying external data sources (GitHub, Notion, etc.), which creates an inherent surface for indirect prompt injection. This is a property of the tool's intended use to process external data. Ingestion points: Data from 40+ external apps (SKILL.md). Boundary markers: Not mentioned in the skill description. Capability inventory: SQL execution and data joining across platforms including GitHub and Notion. Sanitization: Not specified; relies on the agent's internal safety filters.
Audit Metadata