The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from external, untrusted websites, creating a surface for indirect prompt injection attacks.
Ingestion points: Untrusted web data enters the context via the fetch_page, fetch_dynamic, and fetch_stealthy tools, as well as through the provided scrapling_scrape.py and scrapling_smoke_test.py scripts.
Boundary markers: The instructions and scripts do not provide explicit delimiters or warnings (e.g., "ignore embedded instructions") to separate scraped content from the agent's core instructions.
Capability inventory: The skill has capabilities to perform network requests (scraping) and write data to the local file system (saving crawl results via spiders).
Sanitization: There is no evidence of HTML sanitization, escaping, or filtering of the scraped content in the provided scripts before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The documentation guides users to install the scrapling package and the playwright browser automation library. These are standard dependencies required for the skill's operation.
[COMMAND_EXECUTION]: The skill provides numerous examples of shell commands for installing software, configuring MCP servers, and using the Scrapling CLI for extraction tasks.

scrapling-mcp