design-spec-prototyper
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a Python search script (
search.py) located in a companion skill's directory (<UIUX_DIR>) to supplement missing design specifications. This involves the dynamic assembly of shell commands. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data (design documents, PRDs, and screenshots) to drive code generation and external search commands, creating a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read
design.md,prd.md, and design screenshots found within the project scope (SKILL.md). - Boundary markers: There are no explicit instructions to treat these inputs as data or to ignore embedded instructions (absent).
- Capability inventory: The skill can write files (
prototype.html) and execute local Python scripts via subprocess calls. - Sanitization: The skill does not define methods for sanitizing or escaping content extracted from these files before using it to generate prototype code or search queries (absent).
- [EXTERNAL_DOWNLOADS]: The skill references and downloads CSS and font assets from Google Fonts by default to style the generated prototypes. This utilizes a well-known and reputable service.
Audit Metadata