tella-ui-redraw
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by reading labels and values from external product pages and user-provided recording frames.
- Ingestion points: Data enters the context via the
import_from_urlandget_clip_frametools referenced in SKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore potentially malicious text embedded in the source UI elements.
- Capability inventory: The skill uses Tella Motion tools for layout and shape manipulation (
addShape,addTitle,addMedia,create_motion_document). No access to general-purpose system commands or persistent storage is indicated. - Sanitization: There are no explicit instructions for sanitizing or escaping content fetched from external sources.
Audit Metadata