brand-to-design-md
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs to generate documentation and render HTML artifacts, which creates a potential surface for indirect prompt injection.
- Ingestion points: External brand homepages and product pages accessed during the workflow.
- Boundary markers: The skill does not define specific delimiters to isolate external data from instructions.
- Capability inventory: The agent is tasked with file-writing and browser-based verification (e.g., screenshots and console checks).
- Sanitization: No explicit sanitization or validation of the extracted content is mentioned in the workflow.
- Context: This ingestion is required for the skill's primary function of brand analysis and is not indicative of malicious intent.
Audit Metadata