The Agent Skills Directory

[Prompt Injection] (SAFE): The skill consists of design constraints and stylistic rules. No instructions were found that attempt to override system safety guidelines, extract system prompts, or initiate restricted behaviors.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns (curl, wget, fetch) were detected.
[Obfuscation] (SAFE): All content is in plain text. No Base64 encoding, zero-width characters, or homoglyph attacks are present.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not define external package dependencies (npm, pip) or execute remote scripts.
[Persistence & Privilege Escalation] (SAFE): No commands related to system persistence, shell profile modification, or privilege escalation (sudo) were identified.

miro-ui-skills