The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs node -e to execute inline JavaScript for reading the local configuration file and parsing API response data.
[DATA_EXFILTRATION]: Reads the XCRAWL_API_KEY from the local file ~/.xcrawl/config.json and transmits it to the vendor's API endpoint (run.xcrawl.com) for authentication. This is consistent with the skill's stated functionality.
[EXTERNAL_DOWNLOADS]: Communicates with the vendor API at https://run.xcrawl.com and retrieves content from arbitrary URLs provided by the user.
[PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating a risk of indirect prompt injection.
Ingestion points: Scraped content is retrieved from the XCrawl API results in the SKILL.md workflows.
Boundary markers: No specific boundary markers or instructions are provided to the agent to ignore instructions embedded in the retrieved web content.
Capability inventory: The skill is granted access to tools including curl, node, and file manipulation commands (Read, Write, Edit, Grep).
Sanitization: The skill returns raw response bodies from the API without sanitization or filtering.

xcrawl-scrape