thumbnail-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes an HTML export template that fetches font resources from Google Fonts (
fonts.googleapis.com), which is a well-known and trusted service. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external file (
.agents/design-context.md) to inform its design choices. This creates a surface for indirect prompt injection if the source file contains malicious instructions. - Ingestion points: Reads content from
.agents/design-context.mdin Step 1. - Boundary markers: None; the skill assumes the design context is authoritative and safe.
- Capability inventory: No dangerous capabilities detected; the skill primarily generates design prompts and HTML/CSS templates for the agent to present to the user.
- Sanitization: None detected for the ingested context content.
Audit Metadata