The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process large-scale knowledge bases and web pages, which constitute untrusted external data sources.
Ingestion points: The skill utilizes the get_knowledge_by_lines tool to pull content from identifiers such as URLs, document IDs, and file paths as specified in the Input Specification and Processing Pipeline sections.
Boundary markers: The instructions do not define the use of delimiters or specific prompts to ensure the agent ignores or isolates instructions that might be embedded within the ingested text.
Capability inventory: The skill is equipped with ms-playwright for web access, get_knowledge_by_lines for reading content, and add_knowledge for writing summarized information back into a knowledge base.
Sanitization: There is no evidence of content validation, escaping, or sanitization procedures in the Processing Pipeline to prevent malicious data from affecting downstream processing or stored knowledge.

read large webpage or knowledge