after-hours-editorial-template
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from a design document to influence the generation of the final HTML artifact.\n
- Ingestion points: The workflow in
SKILL.mdspecifies reading an activeDESIGN.mdfile to map styles into CSS variables.\n - Boundary markers: The instructions do not define clear delimiters or specific warnings to ignore embedded instructions within the ingested data.\n
- Capability inventory: The skill requires the
file_writecapability to outputindex.html. It does not perform network operations or execute arbitrary shell commands within its primary workflow scripts.\n - Sanitization: No sanitization or validation logic is specified for the values extracted from the design document before they are interpolated into the artifact.\n- [EXTERNAL_DOWNLOADS]: The template fetches scripts and styles from well-known infrastructure providers.\n
- Evidence:
assets/template.htmlloads font resources fromfonts.googleapis.comandfonts.gstatic.com, and includes the GSAP animation library from the official jsDelivr CDN (cdn.jsdelivr.net).
Audit Metadata