The Agent Skills Directory

[SAFE]: No malicious behavior, data exfiltration, or credential exposure was detected in the skill instructions or metadata.- [PROMPT_INJECTION]: The skill uses instructional framing to adopt a specific design agent persona focused on aesthetic goals. This is used for creative guidance and does not attempt to override platform security boundaries or bypass safety filters.- [EXTERNAL_DOWNLOADS]: The skill recommends the use of reputable web frameworks such as Astro, SvelteKit, or Next.js and standard typography like JetBrains Mono. These are well-known industry resources recommended as architectural choices.- [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or instructions for the agent to execute arbitrary system commands.- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found.- [SAFE]: (Indirect Prompt Injection Surface) The skill processes user-provided code for restyling and review. While this provides a surface for indirect prompt injection if the processed code contains malicious instructions, the skill's capabilities are limited to code generation and design advice, posing no significant escalation risk. • Ingestion points: User-provided frontend source code (SKILL.md). • Boundary markers: Absent. • Capability inventory: Code generation and textual advice. • Sanitization: Absent.

frontend-design