The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the belt CLI to run search and extraction tools like tavily/search-assistant and exa/search. This functionality is restricted by the skill's configuration to the specified toolset.
[EXTERNAL_DOWNLOADS]: The skill references the installation of the belt-sh/cli tool and points to documentation hosted on a public GitHub repository. These are identified as standard components of the platform ecosystem used by the skill.
[PROMPT_INJECTION]: The skill is designed to process data from external websites (search results and extracted article content). This creates a surface for indirect prompt injection where malicious instructions embedded in web content could influence the agent's behavior.
Ingestion points: External data enters the agent context through search result summaries and content extraction utilities (e.g., tavily/extract).
Boundary markers: The provided templates do not use specific delimiters to separate user-provided or web-sourced data from the agent's primary instructions.
Capability inventory: The skill possesses the capability to execute belt applications.
Sanitization: No explicit sanitization or filtering of the content retrieved from external sources is described in the instructions.

seo-content-brief