The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from arbitrary external URLs, which creates a surface for indirect prompt injection if the scraped content contains instructions intended to manipulate the agent's behavior.
Ingestion points: The url parameter in the ScrapeConfig object, which is passed to the client.scrape() method in SKILL.md.
Boundary markers: The skill documentation does not provide specific instructions for using delimiters or boundary markers to separate untrusted scraped data from the agent's system instructions.
Capability inventory: The skill possesses the capability to make network requests through the Scrapfly API, perform JavaScript rendering, and execute complex browser interaction scenarios (js_scenario).
Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved content before it is passed back to the agent context.
[EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the scrapfly-sdk package via the system package manager (pip). This is the official SDK provided by the vendor for interacting with their service.

scrapfly-scraper