iii-http-endpoints
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes vendor-specific primitives like
registerWorker,registerFunction, andregisterTriggerto set up the execution environment and route handlers. These are standard operations for theiii-hqplatform. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle external HTTP requests, which is a known vector for untrusted data ingestion.
- Ingestion points: Untrusted data enters the agent context through the
ApiRequestobject fields:body,path_params, andheaders(referenced inSKILL.md). - Boundary markers: No explicit instructions for using delimiters or boundary markers to isolate untrusted web input are provided in the documentation.
- Capability inventory: The skill uses
registerFunctionandregisterTriggerto bind logic to paths, andregisterWorkerfor initialization (referenced inSKILL.md). - Sanitization: There are no specific sanitization or validation routines described for the inbound request data before it is processed by the handler.
Audit Metadata