The Agent Skills Directory

[SAFE]: No security concerns were identified. The skill's functionality is limited to SEO research and analysis using authorized tools.
[EXTERNAL_DOWNLOADS]: The skill references CLI tools from the inference-sh and belt-sh GitHub organizations. These are recognized platform components necessary for the skill's operation and are sourced from the vendor's infrastructure.
[COMMAND_EXECUTION]: The skill provides example commands for the belt utility to perform search and extraction tasks. These operations are restricted to obtaining public web data for SEO purposes and do not involve unauthorized system access.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites to analyze competitor strategies. While this introduces a potential surface for indirect prompt injection from processed web pages, it is a standard and necessary component of the skill's SEO research functionality.
Ingestion points: Data retrieved from external URLs provided to belt app run tavily/extract.
Boundary markers: Absent; external content is processed directly for extraction.
Capability inventory: Use of belt CLI for search, extraction, and image generation.
Sanitization: No specific sanitization or filtering of retrieved web content is performed before processing.

seo-content-brief