ux-ui-developer

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill acts as a UI/UX developer and is designed to ingest and review user-provided front-end code (HTML, CSS, JS) and design specifications. This creates an indirect prompt injection surface where malicious instructions embedded in the reviewed content could attempt to influence the agent's behavior. The potential impact is higher if the agent is connected to the suggested repository management tools.
  • Ingestion points: User-supplied code snippets, design specifications, and usability feedback provided in SKILL.md and references/ui-patterns.md.
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings for external content.
  • Capability inventory: If the user follows the setup instructions in references/integrations.md, the agent gains capabilities to create issues, review merge requests, and manage repository labels via MCP servers for GitHub and GitLab.
  • Sanitization: Absent. There are no instructions for the agent to sanitize or filter user-supplied code before processing.
  • [EXTERNAL_DOWNLOADS]: The documentation in references/integrations.md provides instructions for the user to install external MCP servers from the NPM registry to enable platform integrations.
  • Fetches official packages: @modelcontextprotocol/server-github and @modelcontextprotocol/server-gitlab.
  • Fetches third-party package: @AshDevFr/pusher-channels-mcp-server for real-time UI debugging features.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — ux-ui-developer