iblai-vibe-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads a template for environment configuration from the ibl.ai official GitHub repository.
- [COMMAND_EXECUTION]: The instructions direct the agent to run standard development and testing commands, such as pnpm dev and npx playwright, to verify the application's functional status.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a user interface that ingests and handles workflow definitions, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Workflow definitions are ingested via the API in app/(app)/workflows/[id]/page.tsx and through drag-and-drop data transfer in components/workflows/workflow-canvas.tsx.
- Boundary markers: No explicit instructions were found for implementing boundary markers or system prompts to ignore instructions embedded within the workflow data.
- Capability inventory: The skill possesses capabilities for network operations via RTK Query and local command execution for development and testing.
- Sanitization: The instructions do not define sanitization or validation logic for the processed workflow definition data.
Audit Metadata