figma-to-android
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external Figma handoff bundle, creating a potential surface for indirect prompt injection where malicious instructions could be hidden in design files.\n
- Ingestion points: The agent reads measurements and component structures from
summary/design-summary.jsonas specified in Section 3.\n - Boundary markers: The instructions lack specific guidance on using delimiters or adding warnings to ignore instructions potentially embedded within the design metadata.\n
- Capability inventory: The skill is capable of generating Android UI code and executing build, test, and render commands within the local development environment as described in Section 5.\n
- Sanitization: No explicit sanitization or strict schema validation for the input design summary file is required by the instructions.\n- [COMMAND_EXECUTION]: The skill instructs the agent to perform command-line operations to verify the implementation.\n
- Evidence: Section 5 directs the agent to run the repository's build, test, preview, or render checks to ensure UI parity.
Audit Metadata