authoring-patterns

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates the creation of UI pattern files within a specific project directory. It follows a structured workflow that involves reading local project guidelines and writing TypeScript files to a designated path (projects/internals/patterns/src/).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests HTML templates from conversation context. It manages this attack surface by requiring successful validation via api_template_validate before any file persistence occurs, acting as a security boundary for untrusted data. Every instance of ingested data is validated, and file-write capabilities are restricted to the patterns source directory.
  • [DYNAMIC_EXECUTION]: The skill generates TypeScript source code (.examples.ts) based on user-provided HTML and writes it to the local filesystem. This process is documented as the core purpose of the tool for developer productivity and occurs using predefined templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 05:53 AM
Security Audit — agent-trust-hub — authoring-patterns