AI agents call cross_org_diff to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name alone, 'diff' implies comparison and analysis of data across Salesforce orgs, which is a read-only operation. The incomplete description prevents higher confidence, but there is no evidence of side effects, code execution, deletion, or financial impact. The tool appears designed for querying and analyzing differences rather than modifying state.
From the tool's definition Tool name 'cross_org_diff' suggests comparison/diffing operations; description is incomplete ('USE THIS for any') and uninformative, providing no indication of write, execute, or destructive capabilities.
Attacks that exploit this kind of access
USE THIS for any. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for cross_org_diff: 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 Sfgraph. Nothing to install.
cross_org_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cross_org_diff 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 cross_org_diff. 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.
cross_org_diff is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →