The Agent Skills Directory

Prompt Injection (SAFE): The use of instructional markers such as 'CRITICAL' and 'IMPORTANT' is restricted to design philosophy and aesthetic choices. No attempts to bypass safety filters or extract system prompts were detected.\n- Data Exposure & Exfiltration (SAFE): The skill does not interact with the file system, environment variables, or external networks.\n- Remote Code Execution (SAFE): No download or execution patterns (e.g., curl, npm install, pip install) are present.\n- Obfuscation (SAFE): The text is clear and lacks hidden or encoded content such as Base64, zero-width characters, or homoglyphs.\n- Indirect Prompt Injection (SAFE): While the skill ingests user requirements for UI generation, it lacks the technical capabilities (such as network or file system write access) required for this to become a high-risk vector.

frontend-design