question-refiner
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and examples. It does not perform any sensitive operations such as file system access, network requests, or command execution.
- [NO_CODE]: There are no scripts, executables, or code files associated with this skill. It functions purely as a prompt template for the AI agent.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user research queries. Ingestion points: User input research questions (SKILL.md). Boundary markers: The skill uses structured markdown for output but lacks explicit delimiters or 'ignore' instructions for the initial user input. Capability inventory: The skill has no capability for subprocess calls, network operations, or file writes. Sanitization: There is no explicit sanitization of user input. Given the lack of dangerous capabilities, the risk associated with this injection surface is minimal.
Audit Metadata