AI agents use set_status to create or update resources in Crosswalk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crosswalk environment.
The tool modifies application state but does not delete data or cause irreversible effects. Status changes are typical write operations. Severity is medium because incorrect status changes could cause workflow confusion (e.g., marking an application as rejected when still active), but the effects are recoverable by changing the status again. It does not move money, execute arbitrary code, or permanently destroy data.
From the tool's definition Tool description states it changes application status to one of five states (draft, submitted, interviewing, rejected, offer). This is a reversible modification of data—status values can be updated back and forth without permanently destroying records.
Attacks that exploit this kind of access
Change an application status (draft, submitted, interviewing, rejected, offer). It is categorised as a Write tool in the Crosswalk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crosswalk MCP server in PolicyLayer and add a rule for set_status: 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 Crosswalk. Nothing to install.
set_status 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 set_status 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 set_status. 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.
set_status is provided by the Crosswalk MCP server (mohakgarg5/crosswalk-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 →