skills/skills-101/superpowers/chat-ui/Gen Agent Trust Hub

chat-ui

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of chat component configurations from a remote registry at https://ui.inference.sh/r/chat.json.
  • [COMMAND_EXECUTION]: Provides instructions for the agent to execute shell commands for installing various CLI tools and UI blocks, specifically using npx skills add and npx shadcn@latest add.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a user-facing chat interface that acts as an ingestion point for untrusted data.
  • Ingestion points: ChatInput component (SKILL.md).
  • Boundary markers: Absent; the provided React examples do not demonstrate the use of delimiters for the agent context.
  • Capability inventory: The skill provides UI rendering components; execution capabilities depend on the API implementation integrated by the user.
  • Sanitization: Absent; the boilerplate code does not include input validation or sanitization logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:09 PM
Security Audit — agent-trust-hub — chat-ui