The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the belt-sh/cli and other specialized SEO skills via npx and points to documentation on the inference-sh GitHub repository. These are documented as vendor-controlled resources necessary for the skill's operation.
[COMMAND_EXECUTION]: The skill provides examples of using the belt CLI tool to run external research apps like tavily/search-assistant and exa/search. These operations are conducted within the vendor's platform environment.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow involves fetching and analyzing data from the open web, which introduces a risk of the agent being influenced by malicious instructions embedded in third-party content.
Ingestion points: Data returned by search tools and article extraction apps (tavily/extract, exa/search) used in sections like 'SERP Analysis Process'.
Boundary markers: There are no explicit instructions or delimiters used to separate user/skill instructions from the potentially untrusted external content.
Capability inventory: The skill uses Bash to execute belt CLI commands which interact with external APIs to fetch web data.
Sanitization: The instructions do not specify any validation or sanitization of the external data before it is processed by the agent to generate content structures or briefs.

seo-content-brief