The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions establish a standard expert persona for SEO auditing without attempting to bypass safety filters or override core system instructions.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths (e.g., .ssh, .aws) were found. The skill references legitimate SEO tools like Google Search Console and PageSpeed Insights for user-led diagnostics.
[Obfuscation] (SAFE): No instances of Base64, zero-width characters, or other encoding techniques intended to hide malicious content were detected.
[Remote Code Execution] (SAFE): The skill contains no commands to download, install, or execute external scripts or packages.
[Privilege Escalation] (SAFE): No commands requiring elevated permissions (e.g., sudo, chmod) are present.
[Persistence] (SAFE): No mechanisms to maintain access across sessions, such as modifying startup scripts or cron jobs, were identified.
[Indirect Prompt Injection] (SAFE): The skill has a clear data ingestion surface (reading local marketing context and site details), but it possesses no dangerous capabilities (like subprocess execution or network requests) that could be exploited via malicious input.
[Dynamic Execution] (SAFE): No runtime compilation, unsafe deserialization, or dynamic script generation patterns were found.

seo-audit