skills/iblai/vibe/iblai-vibe-profile/Gen Agent Trust Hub

iblai-vibe-profile

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download configuration templates and project starter files from the vendor's official GitHub repository (github.com/iblai/vibe). These resources are used for initial project scaffolding and configuration.
  • [COMMAND_EXECUTION]: Includes standard shell commands for project initialization, such as git clone, cp, and pnpm install, which are intended for local development setup. It specifically recommends using --ignore-scripts during package installation as a security best practice.
  • [INDIRECT_PROMPT_INJECTION]: Identifies an attack surface where user-provided metadata or profile information (e.g., bios, career history) could potentially contain instructions targeting the LLM during processing. This is a common surface for UI-driven agent skills and is managed by the vendor's SDK.
  • Ingestion points: Reads userData and tenants from localStorage, and fetches profile data via platform APIs.
  • Boundary markers: Not explicitly defined in instructions; implementation is delegated to the @iblai/iblai-js SDK.
  • Capability inventory: Uses network operations for API calls and file operations for local storage.
  • Sanitization: Relies on the vendor's SDK for data handling and presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 03:43 PM