helix-query-authoring
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a documentation and style guide for HelixDB Rust DSL query authoring. It does not contain executable code that performs malicious actions.
- [COMMAND_EXECUTION]: The skill describes query operations such as read, write, and search within the context of a database DSL. It does not instruct the agent to execute arbitrary shell commands or system-level processes.
- [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were detected. While the skill explains how to return data from queries (e.g., using
.returning()), this is a core functional requirement of a database query tool and follows established patterns for variable selection. - [PROMPT_INJECTION]: The instructions do not contain any bypass markers, safety override attempts, or instructions designed to manipulate the agent's core behavior.
- [EXTERNAL_DOWNLOADS]: The skill does not perform or instruct the agent to perform external downloads of untrusted code or scripts.
Audit Metadata