Stop the local Chrome session and clean up resources.
AI agents invoke local_session_stop to trigger actions in Squidlerio. 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.
The tool executes an operation that stops a running Chrome process and performs cleanup. This is neither a read (no data retrieval) nor write (no persistent data modification). It's an active invocation whose effects depend on context. It is not destructive because no data is being deleted or overwritten. It is not financial.
From the tool's definition Tool performs session termination and resource cleanup operations ('Stop the local Chrome session and clean up resources').
Attacks that exploit this kind of access
Stop the local Chrome session and clean up resources. It is categorised as a Execute tool in the Squidlerio MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Squidlerio MCP server in PolicyLayer and add a rule for local_session_stop: 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 Squidlerio. Nothing to install.
local_session_stop 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 local_session_stop 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 local_session_stop. 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.
local_session_stop is provided by the Squidlerio MCP server (squidlerio/squidler-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 →