The Agent Skills Directory

[Prompt Injection] (SAFE): No override instructions, jailbreak attempts, or system prompt extraction patterns were detected. The content is exclusively focused on design advice.
[Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns are present. External links point to legitimate design resource websites.
[Obfuscation] (SAFE): No Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were found in the content.
[Unverifiable Dependencies & RCE] (SAFE): No package managers (npm, pip, etc.) or remote script download/execution patterns are utilized.
[Privilege Escalation] (SAFE): The skill contains no commands related to privilege escalation or administrative access.
[Persistence Mechanisms] (SAFE): No mechanisms for maintaining persistence, such as shell profile modifications or cron jobs, are included.
[Metadata Poisoning] (SAFE): Metadata fields (name, description) are accurate and do not contain hidden malicious instructions.
[Indirect Prompt Injection] (SAFE): The skill does not ingest external untrusted data and lacks any side-effect capabilities (no file writes, no command execution), resulting in no exposure to injection attacks.
[Time-Delayed / Conditional Attacks] (SAFE): No conditional logic or time-based triggers were detected.
[Dynamic Execution] (SAFE): There is no evidence of dynamic code generation, runtime compilation, or unsafe deserialization.

frontend-design-philosophy