verify-design
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the instructions and metadata shows no signs of prompt injection, obfuscation, or unauthorized system access. The skill follows best practices for a specific developer workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by having the agent ingest and act upon external data in the form of application renderings.
- Ingestion points: Rendered UI screens and screenshots (SKILL.md).
- Boundary markers: None present to distinguish between intended UI and potentially injected content within the rendered view.
- Capability inventory: The agent has the capability to edit project files, including components and styles, based on the input (SKILL.md).
- Sanitization: No explicit sanitization or validation of the rendered content is performed before the agent makes changes to the codebase.
Audit Metadata