The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the scrapling package and its dependency profiles (parser, fetchers, shell, ai, all) from the Python Package Index (PyPI), which is a well-known and trusted package registry.
[COMMAND_EXECUTION]: The skill utilizes local bash scripts (scripts/install.sh, scripts/run-extract.sh, scripts/run-mcp.sh) to manage the setup and operation of the scraping tools. These scripts serve as wrappers for the scrapling CLI and do not perform unauthorized or hidden actions.
[PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection because it is designed to fetch and process arbitrary data from external websites. * Ingestion points: Untrusted data enters the agent context through the Fetcher classes, the scrapling extract command, and the MCP server tools. * Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the fetched content. * Capability inventory: The skill utilizes the Bash, Write, Read, and WebFetch tools, providing a high-capability environment for acting on processed data. * Sanitization: The skill converts content to formats like Markdown or HTML but does not explicitly perform security-focused sanitization of potential injection vectors.

scrapling