sf-ui-design
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local project scripts using Node.js, specifically
.specforge/core/scripts/instructions.mjsandcreate-artifact.mjs. These commands are used to manage workflow states and generate design artifacts within the host project directory. - [PROMPT_INJECTION]: The skill processes untrusted input from intake and requirement files, creating an indirect prompt injection surface. This is a functional requirement for its role in translating requirements into UI designs.
- Ingestion points:
00-intake/brief.md,00-intake/prd.md,01-spec/requirements.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: The skill can execute local Node.js scripts and write to the project's specification directory.
- Sanitization: There are no explicit instructions for sanitizing or validating the content of the requirements files.
- [SAFE]: The skill's operations are confined to the local project environment and involve no remote downloads, credential access, or persistence mechanisms.
Audit Metadata