pencil-design
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external .pen files via pencil_batch_get and pencil_get_editor_state. * Ingestion points: Node data and schemas are read from external files. * Boundary markers: There are no instructions to use delimiters or ignore embedded instructions within the design data. * Capability inventory: The skill can modify design files and generate React/Next.js code. * Sanitization: The instructions do not mandate sanitizing or validating external content before it is used for code generation or design updates.
Audit Metadata