flutter-design
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a collection of design guidelines and workflow instructions for Flutter development. It does not execute arbitrary shell commands, access sensitive system files, or perform unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates an analysis phase that reads external repository data (such as
pubspec.yaml, app structure, and current git state) and processes user-provided screenshots, which constitutes a standard ingestion surface for design tasks. - Ingestion points: Flutter project files (
pubspec.yaml, theme files, reusable widgets), git status, and visual screenshots as defined inSKILL.md. - Boundary markers: The instructions do not explicitly define delimiters for untrusted file content.
- Capability inventory: The workflow involves code generation (UI implementation) and the invocation of specialized sub-agents for auditing and QA, though no direct dangerous system capabilities are exposed in the provided instructions.
- Sanitization: No specific filtering or sanitization of input data is described; the skill relies on the agent's internal safety guardrails.
Audit Metadata