Skills
skills/jh941213/my-claude-code-asset/stitch-react/Gen Agent Trust Hub

stitch-react

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads HTML content from a URL provided by the Stitch service (a Google-affiliated platform). This is a core part of the transformation workflow.
  • [COMMAND_EXECUTION]: Utilizes the Bash tool to run standard development commands such as npx tsc for type checking and npx eslint for code linting.
  • [PROMPT_INJECTION]: The skill processes external HTML data as input for code generation, creating a surface for indirect prompt injection.
  • Ingestion points: source.html (downloaded from an external Stitch URL) and DESIGN.md (local file).
  • Boundary markers: Absent. The skill does not explicitly use delimiters or instructions to ignore embedded commands in the input HTML.
  • Capability inventory: Bash (shell execution), Write (file modification), and Edit (file modification) tools are enabled.
  • Sanitization: Absent. No mention of escaping or validating the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:04 PM