Send instructions to an active AI process (Claude Code or Gemini CLI)
AI agents invoke update_task to trigger actions in SystemPrompt Coding Agent. 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.
This tool sends arbitrary instructions to an active AI coding process that autonomously executes programming tasks on a local development environment. The instructions could cause the AI agent to run code, modify files, execute shell commands, or perform other operations. Since the effects depend entirely on what instructions are sent and the AI agent can take broad autonomous actions, this is Execute category.
From the tool's definition "Send instructions to an active AI process (Claude Code or Gemini CLI)" — directs an autonomous AI coding agent to perform actions
Documented attack patterns abuse exactly the kind of access update_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SystemPrompt Coding Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for update_task:
{
"version": "1",
"default": "deny",
"tools": {
"update_task": {
"limits": [
{
"counter": "update_task_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}update_task stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send instructions to an active AI process (Claude Code or Gemini CLI). It is categorised as a Execute tool in the SystemPrompt Coding Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SystemPrompt Coding Agent MCP server in PolicyLayer and add a rule for update_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 SystemPrompt Coding Agent. Nothing to install.
update_task 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 update_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 update_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.
update_task is provided by the SystemPrompt Coding Agent MCP server (systempromptio/systemprompt-code-orchestrator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 SystemPrompt Coding Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 SystemPrompt Coding Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.