刪除已攝入的 DOCX/DFM 文件及其本地 artifacts。
AI agents call delete_docx to permanently remove resources in Asset Aware — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes files and their artifacts. Deletion cannot be undone, making it Destructive rather than Write. The high severity reflects the risk that an AI agent could permanently remove important documents; the confidence is very high due to the explicit 'delete' semantics in both the tool name and description.
From the tool's definition delete_docx - 刪除已攝入的 DOCX/DFM 文件及其本地 artifacts (translates to: 'Delete ingested DOCX/DFM files and their local artifacts'). The verb '刪除' (delete) explicitly indicates irreversible removal of data.
Attacks that exploit this kind of access
刪除已攝入的 DOCX/DFM 文件及其本地 artifacts。. It is categorised as a Destructive tool in the Asset Aware MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Asset Aware MCP server in PolicyLayer and add a rule for delete_docx: 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 Asset Aware. Nothing to install.
delete_docx 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_docx 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_docx. 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_docx is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). 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 →