The Agent Skills Directory

[DATA_EXFILTRATION]: The skill uses environment variables to handle API credentials (SCRAPFLY_API_KEY), which is a secure and recommended practice to avoid hardcoding sensitive secrets.
[PROMPT_INJECTION]: The skill is inherently exposed to indirect prompt injection as its primary function is to process and extract data from untrusted web content using LLMs. Ingestion points: The 'body' parameter in ExtractionConfig accepts raw HTML, markdown, or text from external sources. Boundary markers: No explicit delimiters or boundary markers are demonstrated in the example prompts to distinguish instructions from external data. Capability inventory: The skill allows network communication with the Scrapfly API and returns extracted data results to the agent. Sanitization: External web content is processed by the Scrapfly API without documented pre-sanitization steps.

scrapfly-extraction