Skills
Navigate
skills/android/skills/ink-app-builder/Gen Agent Trust Hub

ink-app-builder

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated and stored stroke data, which represents an attack surface for indirect prompt injection.
  • Ingestion points: BrushFamily.decode and StrokeInputBatch.decode are used to deserialize data from InputStream and ByteArray sources in references/android/develop/ui/compose/touch-input/stylus-input/ink-api-brush-apis.md and references/persistence-and-advanced.md.
  • Boundary markers: No explicit boundary markers or delimiters are implemented to separate data from instructions during processing.
  • Capability inventory: The skill possesses file-writing capabilities via FileOutputStream for image export and database write access via Room (references/persistence-and-advanced.md).
  • Sanitization: The implementation relies on basic try-catch error handling during deserialization without performing logic-level sanitization of the decoded content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 09:31 PM