instrument-designer
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill defines a rigorous framework for designing MEL/SRHR instruments, referencing established citations such as Groves et al. (2009) and Willis (2005).
- [COMMAND_EXECUTION]: The skill utilizes vendor-specific tool calls (ane_package.reporting.word_export and xlsform.write_xlsform) to generate Word and XLSForm documents. These are functional components of the agent's reporting capabilities within the gasserane ecosystem.
- [PROMPT_INJECTION]: The skill processes user-supplied measurement targets and existing instruments, creating an indirect prompt injection surface.
- Ingestion points: Measurement target and existing instruments provided by the user.
- Boundary markers: None specified to separate untrusted data from instructions.
- Capability inventory: File creation and modification via export functions and the agent's Edit tool.
- Sanitization: No explicit sanitization or validation of the input content is documented.
Audit Metadata