hive-build
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard integration patterns for Hive's MCP and REST APIs across several languages (TypeScript, Python, Go, Rust, Java).
- [CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing the user to manage secrets via environment variables (e.g., HIVE_API_KEY) and explicitly warns against exposing keys to client-side code.
- [EXTERNAL_DOWNLOADS]: Code patterns reference the official
hive-mcp-clientpackage and connect to vendor-controlled endpoints atmcp.hiveintelligence.xyz. These are legitimate resources for the skill's intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill proactively addresses potential injection/autonomy risks by requiring explicit user approval for stateful operations and explicitly advising developers against deriving consent from model output.
Audit Metadata