The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to scrape content from arbitrary external websites. This exposes the agent to indirect prompt injection, where malicious instructions embedded in a web page could attempt to override the agent's behavior. * Ingestion points: Content fetched from external URLs via npx webcrawl scrape (SKILL.md). * Boundary markers: There are no instructions provided to the agent to treat scraped content as untrusted or to use specific delimiters. * Capability inventory: The skill executes network requests and shell commands. * Sanitization: The instructions do not mention any sanitization or validation of the retrieved web content.
[COMMAND_EXECUTION]: The skill relies on executing shell commands (npx webcrawl) to scrape websites and diagnose issues. These are the primary tools for the skill's intended purpose.
[EXTERNAL_DOWNLOADS]: The skill uses npx to run the webcrawl package. This involves downloading and executing code from the npm registry at runtime. As the tool is associated with the author, it is considered a vendor-provided resource.

webcrawl-protected-sites