The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary external websites, which creates a surface for indirect prompt injection.
Ingestion points: External content is fetched through the url (Map/Crawl) and urls (Batch) parameters in SKILL.md.
Boundary markers: The instructions suggest using markdown or text formats for LLM context, but the skill does not define specific boundary delimiters for the ingested content in its instructions.
Capability inventory: The skill performs network operations via the requests library and provided SDKs to interact with the crawler API.
Sanitization: The instructions do not specify sanitization or filtering of the content extracted from external sites.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the scavio library via pip and npm, and to run the @scavio/mcp-server using npx. These resources are the official distribution tools for the service provided by the author.
[COMMAND_EXECUTION]: The skill documentation includes shell command examples for setting environment variables (export) and installing software via package managers (pip, npm, npx).

website-crawler-api