The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites which could contain malicious instructions designed to manipulate the agent.
Ingestion points: Data enters the system via Puppeteer's page.goto and Axios's axios.get functions in SKILL.md.
Boundary markers: The instructions lack delimiters to separate scraped content from agent instructions.
Capability inventory: The skill has network access and browser automation capabilities through the puppeteer and axios libraries.
Sanitization: The skill extracts text via CSS selectors but does not filter for embedded prompt injection patterns.

web-scraper