특정 회사 문서를 삭제합니다.
AI agents call delete_company_document to permanently remove resources in OOSDK MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes company documents without any indication of recovery, undo, or soft-delete capability. Deletion is irreversible and represents a clear Destructive action. Severity is high because unintended deletion of company documents could harm business operations, compliance, and data integrity.
From the tool's definition Tool name 'delete_company_document' and description '특정 회사 문서를 삭제합니다' (Korean: 'Delete a specific company document') indicate irreversible deletion of data.
Attacks that exploit this kind of access
특정 회사 문서를 삭제합니다. It is categorised as a Destructive tool in the OOSDK MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the OOSDK MCP Server MCP server in PolicyLayer and add a rule for delete_company_document: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches OOSDK MCP Server. Nothing to install.
delete_company_document is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_company_document rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for delete_company_document. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
delete_company_document is provided by the OOSDK MCP Server MCP server (sunnylabtv-crypto/ai_mcp_multi_agent_oosdk-public). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →