The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to fetch content from arbitrary URLs, which may contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Web content retrieved via the page_reader function and the z-ai-web-dev-sdk, as documented in SKILL.md and implemented in scripts/web-reader.ts.
Boundary markers: The instructions do not specify the use of delimiters or instructions for the agent to ignore potentially malicious content embedded in the scraped data.
Capability inventory: The skill utilizes network capabilities to retrieve HTML, text, and metadata from external web sources.
Sanitization: While the SDK parser clean metadata, there are no instructions for the agent to sanitize or validate the content before processing it within its context.

web-reader