deck-guizang-editorial
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches resources from well-known services, specifically Tailwind CSS via CDN and typography from Google Fonts.
- [PROMPT_INJECTION]: The skill acts as a template for user content, presenting a surface for indirect prompt injection. 1. Ingestion points: User content provided via prompt is used to populate layout slides (L01-L10) defined in SKILL.md. 2. Boundary markers: No explicit delimiters or boundary markers for user content are present. 3. Capability inventory: The skill generates HTML and CSS code to render slides. 4. Sanitization: No sanitization or filtering of user-provided content is specified in the instructions. This surface is considered safe as it is limited to document generation.
- [SAFE]: Analysis of the instructions and example code reveals no evidence of malicious behavior, obfuscation, or data exfiltration. The skill is designed as a presentation layout template.
Audit Metadata