Suggest a salary decrease for an underperforming colleague
AI agents use decrease_coworker_salary to commit financial operations through Hilanet MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Despite the satirical framing, this tool explicitly involves adjusting (decreasing) salary/compensation for another person, placing it in the Financial category. The action targets another employee's financial standing. Severity is high because misuse could (even in simulation) model or trigger real financial harm to a coworker.
From the tool's definition 'Suggest a salary decrease for an underperforming colleague' — directly relates to modifying financial compensation
Documented attack patterns abuse exactly the kind of access decrease_coworker_salary gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hilanet MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for decrease_coworker_salary:
{
"version": "1",
"default": "deny",
"tools": {
"decrease_coworker_salary": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to decrease_coworker_salary is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Suggest a salary decrease for an underperforming colleague. It is categorised as a Financial tool in the Hilanet MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Hilanet MCP server in PolicyLayer and add a rule for decrease_coworker_salary: 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 Hilanet MCP. Nothing to install.
decrease_coworker_salary is a Financial 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 decrease_coworker_salary 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 decrease_coworker_salary. 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.
decrease_coworker_salary is provided by the Hilanet MCP server (adird/hilanet-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Hilanet MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 Hilanet MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.