The Agent Skills Directory

[Prompt Injection] (SAFE): The skill uses instructional emphasis markers like 'CRITICAL' and 'IMPORTANT' to define design quality and aesthetic direction. These do not attempt to bypass safety guardrails or override system instructions.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns (e.g., curl, fetch) were detected.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not attempt to install external packages or download/execute remote scripts.- [Indirect Prompt Injection] (SAFE): While the skill processes user requirements to generate code, it lacks execution capabilities or administrative triggers. (1) Ingestion points: User requirements defined in SKILL.md. (2) Boundary markers: None. (3) Capability inventory: Code generation (HTML/CSS/JS). (4) Sanitization: None. Result: The surface is limited to stylistic output generation.- [Obfuscation] (SAFE): The content is provided in clear text with no evidence of Base64, zero-width characters, or homoglyph-based evasion techniques.- [Persistence Mechanisms] (SAFE): No attempts to modify system configurations, shell profiles, or scheduled tasks were found.

frontend-design