The Agent Skills Directory

[SAFE] (SAFE): The skill is entirely composed of natural language instructions and markdown documentation. No malicious patterns, obfuscation, or unauthorized commands were detected.
[NO_CODE] (INFO): This is a no-code skill. It defines a framework for the agent's behavior and response structure but does not include scripts, binaries, or dependency files.
[INDIRECT_PROMPT_INJECTION] (INFO): While the skill instructs the agent to process external data (such as robots.txt and website content), it lacks the internal capabilities to execute code or exfiltrate data. The output is limited to generating an audit report for the user, placing it in the lowest risk tier for indirect injection.

seo-audit