diagram-design-editorial
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references web fonts from Google Fonts and the JSDelivr CDN for rendering diagrams.
- [COMMAND_EXECUTION]: Installation involves standard developer workflows such as cloning a repository from GitHub and using package runners like npx.
- [DATA_EXFILTRATION]: Provides a feature to fetch external website content at the user's request to extract brand colors and fonts.
- [PROMPT_INJECTION]: Ingesting external website content for brand onboarding creates a potential surface for indirect prompt injection.
- Ingestion points: External URLs processed during the brand onboarding phase in SKILL.md.
- Boundary markers: None explicitly defined for website content parsing.
- Capability inventory: Writes configuration to local reference files and generates diagram files.
- Sanitization: Automated color contrast validation is performed, but general content sanitization is not detailed.
Audit Metadata