skills/coollabsio/coolify/shadcn/Gen Agent Trust Hub

shadcn

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the shadcn CLI (via npx, pnpm, or bunx) to perform project management tasks, such as searching registries, viewing component metadata, and initializing configurations.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of UI components and configurations from official shadcn registries and third-party GitHub repositories. To mitigate supply chain risks, the instructions mandate the use of --dry-run, --diff, and --view flags for manual code inspection before installation.
  • [DYNAMIC_CONTEXT_INJECTION]: A load-time command (npx shadcn@latest info --json) is used to inject project-specific configuration details—including import aliases, framework versions, and installed components—into the agent's context to ensure accurate guidance.
  • [INDIRECT_PROMPT_INJECTION]: The agent is instructed to fetch documentation and examples from external URLs. The skill establishes a mandatory review process for all added or updated code to ensure that external content does not contain malicious instructions or unexpected behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:22 PM
Security Audit — agent-trust-hub — shadcn