good-ui-bobby

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download resources from an external domain not recognized as an official repository or well-known service. Evidence: npx shadcn@latest add https://bazza.dev/r/hit-area in references/interaction-defaults.md.
  • [REMOTE_CODE_EXECUTION]: The use of npx shadcn add with a remote URL enables the automated retrieval and integration of third-party code into the local project. The registry at https://bazza.dev/r/hit-area delivers component code and configuration that is merged into the workspace without verification.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage project state and dependencies, including Git initialization and package additions via npx.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of untrusted codebase data. 1. Ingestion points: Local project file inspection and dependency analysis (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Shell command execution (git, npx) and project file modifications. 4. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 02:37 AM
Security Audit — agent-trust-hub — good-ui-bobby