design-init
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the local project environment, which introduces a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill performs an inspection of the project's current state, including its package manager, React setup, and existing CSS theme or token files (SKILL.md, Step 1).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed project files are specified in the workflow.
- Capability inventory: The skill is capable of invoking sub-skills, executing tools like DesignSync to list projects, and writing a
design.manifest.jsonfile to the repository root. - Sanitization: There are no mentioned mechanisms for sanitizing or validating the contents of the inspected project files before they influence the agent's orchestration logic.
Audit Metadata