skills/bergside/typeui-cursor/typeui/Gen Agent Trust Hub

typeui

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches content from the author's official GitHub repository (bergside/awesome-design-skills) to index and pull design skill files.
  • [COMMAND_EXECUTION]: The instructions direct the agent to use the TypeUI CLI to perform operations such as listing, installing, pulling, and updating files (e.g., using deterministic flags like --format skill -p cursor).
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests data from a remote registry to generate or update files in the local environment.
  • Ingestion points: External registry index and design skill files are fetched from https://raw.githubusercontent.com/bergside/awesome-design-skills/main/skills/.
  • Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within the ingested skill files.
  • Capability inventory: The skill allows the agent to generate and update files within the user's project using the TypeUI CLI.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the design skill files retrieved from the remote repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:07 PM
Security Audit — agent-trust-hub — typeui