to-artifact
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches typography assets from Google's well-known font services (
fonts.googleapis.comandfonts.gstatic.com) to apply the 'Familjen Grotesk', 'Google Sans Code', and 'Inter' typefaces inreferences/design.md. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for potentially untrusted data from external sources.
- Ingestion points: In
SKILL.md(Step 1), the skill instructions direct the agent to take the 'subject' from sources like session history, Pull Requests, or issues. - Boundary markers: The instructions do not specify any boundary markers or instructions to ignore embedded commands within the ingested PR or issue data.
- Capability inventory: The skill is capable of generating HTML and CSS 'Artifacts' for display in the agent interface.
- Sanitization: The skill lacks explicit sanitization steps for the 'subject' text before it is used to frame the artifact's output.
Audit Metadata