The Agent Skills Directory

Prompt Injection (LOW): The skill is susceptible to Indirect Prompt Injection because it processes content from external documents that could contain malicious instructions. \n
Ingestion points: The tool mcp__lark__docx_v1_document_rawContent retrieves document text, and mcp__lark__wiki_v1_node_search retrieves wiki content. \n
Boundary markers: No specific delimiters or safety instructions are provided to the agent to treat document content as untrusted data or to ignore embedded instructions. \n
Capability inventory: The skill includes the powerful tool mcp__lark__drive_v1_permissionMember_create, which allows the agent to grant 'view', 'edit', or 'full_access' permissions to users. \n
Sanitization: No sanitization or validation of the retrieved document content is described before the agent processes it, allowing content to influence agent logic.

lark-docs