Skills
Navigate
skills/magentosh/superpowers/chat-ui/Gen Agent Trust Hub

chat-ui

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches component registry data from a remote URL (https://ui.inference.sh/r/chat.json) to integrate UI blocks.
  • [COMMAND_EXECUTION]: The instructions recommend running shell commands to install the CLI tool (npx skills add belt-sh/cli) and add the chat components via the shadcn CLI.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides UI components like ChatMessage intended to render content that may come from untrusted sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: The content prop in the ChatMessage component (referenced in SKILL.md).
  • Boundary markers: No explicit delimiter usage or instructions to ignore embedded commands are shown in the component examples.
  • Capability inventory: The skill itself focuses on UI rendering and does not include internal logic for file system modification or network exfiltration.
  • Sanitization: The provided code snippets do not demonstrate explicit sanitization or escaping of the message content before rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — chat-ui