The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not include any executable scripts, binaries, or commands. It provides a structured methodology for evaluating content citability and structural readability.
[NO_CODE]: No code or scripts are included in the skill. The logic resides purely in the natural language instructions provided to the agent for report generation.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external web content (e.g., robots.txt, llms.txt, and website passages), which represents an untrusted data ingestion surface. However, the risk is negligible because the skill does not grant the agent any dangerous capabilities, such as code execution or network exfiltration, which could be exploited through these ingestion points.

seo-geo