The Agent Skills Directory

[Prompt Injection] (SAFE): The content consists of educational documentation and technical guidance. No instructions were found that attempt to bypass AI safety filters, extract system prompts, or override agent behavior.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns were detected. All code snippets are standard front-end templates.- [Remote Code Execution] (SAFE): The skill does not perform any external downloads or execute remote scripts. It provides static SCSS and TypeScript examples for the user's reference.- [Obfuscation] (SAFE): No Base64 encoding, zero-width characters, or homoglyphs were identified in the text or code blocks.- [Indirect Prompt Injection] (SAFE): Ingestion point: The sourceColor variable in the ThemeService example. Boundary markers: None. Capability inventory: No subprocess calls, file-write operations, or network requests are present in the skill scripts. Sanitization: None. Because the skill lacks any execution capabilities, this surface presents no risk.

material-design-3