The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to perform HTTP POST requests to the ScrapeNinja API and jq to process the resulting JSON data. These operations are restricted to the intended functionality of the service.
[EXTERNAL_DOWNLOADS]: The skill facilitates communication with external API endpoints at scrapeninja.p.rapidapi.com to retrieve web content. These are well-known services for the stated purpose of the skill.
[DATA_EXFILTRATION]: Authentication is handled by passing a user-provided API key from the SCRAPENINJA_TOKEN environment variable to the external API service via HTTP headers. This is standard practice for API integration.
[PROMPT_INJECTION]: As a web scraping tool, the skill processes untrusted data from external websites. This represents a potential surface for indirect prompt injection.
Ingestion points: Scraped HTML/JSON content from arbitrary user-provided URLs.
Boundary markers: None explicitly defined in the prompt templates.
Capability inventory: File writing to /tmp, curl network operations, and jq parsing.
Sanitization: No explicit sanitization or filtering of the scraped content is described in the instructions.

scrapeninja