The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system behavior or bypass safety guidelines were found. The skill uses standard instructional language to guide aesthetic choices.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. All code snippets are focused on frontend presentation logic.
[OBFUSCATION]: No Base64-encoded strings, zero-width characters, homoglyphs, or other obfuscation techniques were identified in the markdown or code snippets.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It references standard, well-known UI packages (e.g., react-native-paper, shopify/react-native-skia) that are common in the developer community.
[INDIRECT_PROMPT_INJECTION]: The skill has a low attack surface for indirect injection. While it processes user descriptions of UI styles, it does so through fuzzy matching to internal guides and does not expose sensitive capabilities or perform unsafe interpolation.
[DYNAMIC_CONTEXT_INJECTION]: No shell execution patterns or !command syntax were found in any of the analyzed files.

design-it