AI agents call cache_task_get_status to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name strongly suggests it retrieves status information about cache tasks without modifying or executing anything. Status checks are read operations with no side effects. The 'get_' prefix and '_status' suffix are characteristic of informational queries. Confidence is moderately high based on naming convention, but slightly reduced due to lack of descriptive detail.
From the tool's definition Tool name 'cache_task_get_status' indicates retrieval of cache task status information. The naming convention (get_status) and cache management context suggest read-only querying of cache operation state.
Attacks that exploit this kind of access
cache_task_get_status. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for cache_task_get_status: 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 M365. Nothing to install.
cache_task_get_status 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 cache_task_get_status 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 cache_task_get_status. 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.
cache_task_get_status is provided by the M365 MCP server (robin-collins/m365-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 →