visual-hierarchy-refactoring
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze untrusted source code from external component files, which creates a potential surface for indirect prompt injection if those files contain adversarial instructions.
- Ingestion points: The skill reads file content for components or screens specified by the user in Step 1.
- Boundary markers: The instructions do not include delimiters or specific guardrails to ensure the agent ignores natural language instructions that might be hidden in code comments or string literals within the target files.
- Capability inventory: The skill's primary function is generating refactored CSS and TSX code; it does not explicitly define instructions for shell execution, network exfiltration, or file modification within its core logic.
- Sanitization: The skill lacks mechanisms for sanitizing or validating the ingested code before it is processed by the agent.
Audit Metadata