AI agents use jobhound_update to create or update resources in JobHound — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JobHound environment.
The tool creates or modifies data (job status) in a reversible manner. While it changes application state, it does not delete data, execute arbitrary code, or move money. The 'medium' severity reflects that status updates could affect job search automation flow and potentially trigger downstream actions, but the change is non-destructive and localized to metadata rather than application logic or financial impact.
From the tool's definition Tool name contains 'update' and description states 'Manually update a job's status' — this modifies state of a job tracking record.
Attacks that exploit this kind of access
Manually update a job's status. It is categorised as a Write tool in the JobHound MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JobHound MCP server in PolicyLayer and add a rule for jobhound_update: 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 JobHound. Nothing to install.
jobhound_update 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 jobhound_update 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 jobhound_update. 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.
jobhound_update is provided by the JobHound MCP server (null-phnix/jobhound). 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 →