Raw task splitting without analysis
AI agents use split_tasks_raw to create or update resources in MCP Shrimp Task Manager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Shrimp Task Manager environment.
This tool appears to split or decompose tasks into subtasks, which is a write/create operation within the task management system. 'Raw' suggests it skips analysis steps and directly creates/modifies task structures. The description is minimal, so confidence is moderate. No evidence of deletion, execution of code, or financial operations.
From the tool's definition 'Raw task splitting without analysis' and tool name 'split_tasks_raw'
Attacks that exploit this kind of access
Raw task splitting without analysis. It is categorised as a Write tool in the MCP Shrimp Task Manager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Shrimp Task Manager MCP server in PolicyLayer and add a rule for split_tasks_raw: 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 MCP Shrimp Task Manager. Nothing to install.
split_tasks_raw is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the split_tasks_raw 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 split_tasks_raw. 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.
split_tasks_raw is provided by the MCP Shrimp Task Manager MCP server (samihalawa/gist-task-manager-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 →