check_web_task
AI agents call check_web_task to retrieve information from Gemini Web Automation MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'Check' typically implies retrieval or status verification without side effects. In the context of a web automation system managing tasks, this likely queries task state, progress, or results. No indication of data modification, deletion, code execution, or financial operations. The lack of description reduces confidence slightly, but the read-like semantics and task management context support Read classification.
From the tool's definition Tool name 'check_web_task' suggests querying or monitoring the status of an ongoing web automation task. The empty description limits confidence, but the naming pattern aligns with read-only inspection operations.
Attacks that exploit this kind of access
check_web_task. It is categorised as a Read tool in the Gemini Web Automation MCP MCP Server, which means it retrieves data without modifying state.
Register the Gemini Web Automation MCP server in PolicyLayer and add a rule for check_web_task: 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 Gemini Web Automation MCP. Nothing to install.
check_web_task is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_web_task 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 check_web_task. 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.
check_web_task is provided by the Gemini Web Automation MCP server (vincenthopf/computer-use-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 →