AI agents invoke lock_session to trigger actions in Sysprobe. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Locking the screen triggers an external system operation (activating the screen lock/session lock). It is not purely data retrieval, not a destructive deletion, and not financial. It executes a system action that affects the user session state. Misuse could lock out legitimate users, but the effect is reversible (unlocking with credentials), so it does not qualify as Destructive.
From the tool's definition [ACTION] Lock the screen.
Attacks that exploit this kind of access
[ACTION] Lock the screen. It is categorised as a Execute tool in the Sysprobe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sysprobe MCP server in PolicyLayer and add a rule for lock_session: 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 Sysprobe. Nothing to install.
lock_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the lock_session 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 lock_session. 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.
lock_session is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →