critique
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests HTML artifacts from the project or user input to perform design reviews, creating a potential surface for indirect prompt injection. Ingestion points: Project files or pasted HTML content in the project directory. Boundary markers: None mentioned in the instructions. Capability inventory: Emits HTML reports via the artifact tag. Sanitization: No explicit content sanitization mentioned for the input HTML.
- [EXTERNAL_DOWNLOADS]: The generated report includes references to Google Fonts, which is a well-known and safe service.
Audit Metadata