Save all attachments of a message into save_to_path (must be an existing dir inside ALLOWED_ROOTS).
AI agents use extract_attachments to create or update resources in Nexus Core — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nexus Core environment.
The tool writes/saves files to the local filesystem. While it reads attachment data from a message, the primary action is persisting files to disk, making it a Write operation. Misuse could lead to writing unwanted or malicious files to allowed directories, hence medium severity.
From the tool's definition Save all attachments of a message into save_to_path (must be an existing dir inside ALLOWED_ROOTS)
Attacks that exploit this kind of access
Save all attachments of a message into save_to_path (must be an existing dir inside ALLOWED_ROOTS). It is categorised as a Write tool in the Nexus Core MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nexus Core MCP server in PolicyLayer and add a rule for extract_attachments: 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 Nexus Core. Nothing to install.
extract_attachments is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the extract_attachments 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 extract_attachments. 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.
extract_attachments is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →