hive-tool-discovery
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a secure discovery procedure that mandates schema inspection (
get_api_endpoint_schema) before any tool invocation, preventing common errors associated with malformed or unvalidated API calls. - [SAFE]: All resources (
hive://toolsets,hive://providers, etc.) and tools (search_tools,invoke_api_endpoint) used are internal to the vendor's ecosystem, specifically designed for providing context without exposing sensitive system data. - [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized credential access was found. The skill's metadata and instructions are consistent with its stated purpose of facilitating tool discovery.
- [SAFE]: While the skill ingests data from external Hive resources, the risk of indirect prompt injection is minimized by the use of structured JSON schemas and the requirement for schema-valid arguments during execution.
Audit Metadata