The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external Flutter application code and UI structures, which serves as an ingestion point for untrusted data. While malicious instructions could be embedded in code comments or widget metadata, the skill's capabilities are limited to generating documentation and advice. * Ingestion points: The skill analyzes app screens, interactive elements, and image semantics as part of its auditing workflow. * Boundary markers: No specific delimiters or safety instructions are provided to distinguish between the audited code and the agent's control instructions. * Capability inventory: The skill is authorized to write findings to a local markdown file (docs/quality/accessibility_review.md) and provide UI fix recommendations. * Sanitization: No explicit sanitization or filtering of external code content is described.
[SAFE]: The skill does not perform network operations, execute shell commands, or access sensitive system files. The instructions are aligned with industry-standard accessibility auditing practices for mobile applications.

flutter-accessibility