The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains executable shell commands using curl and bash for tasks such as identifying next-page links, verifying record counts, and managing a local file cache for crawled content.
[EXTERNAL_DOWNLOADS]: The skill references a GitHub repository (github.com/manypicom/lead-gen-playbooks) for lead generation playbooks and instructs the agent to add an external MCP server from a remote URL (https://mcp.manypi.com/mcp). These resources are hosted by the skill's authoring vendor.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to automate the traversal and extraction of data from arbitrary external websites, creating a surface for indirect prompt injection.
Ingestion points: The crawl and paginate functions in the Python snippets process HTML and JSON content from user-specified URLs.
Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings for the fetched content.
Capability inventory: The skill uses network operations (requests.get, curl) and file system access for caching results.
Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external sites before it is processed by the agent.

pagination-and-crawling