High-risk tools in Agentled
4 of the 56 tools in Agentled are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
chatExecute 3/5Send a message to the AgentLed AI agent and get a response. The agent can reason, plan, and build workflows through natural language conversation — no need to construct pipeline...
-
doExecute 3/5Semantic intent router — describe what you want to accomplish in plain English and Agentled will find the best matching live workflow in your workspace. Optionally auto-executes...
-
start_workflowExecute 3/5Start a workflow execution. Optionally provide input data that maps to the workflow's input page fields. For example, if the workflow expects "company_url", pass: { input: { com...
-
stop_executionExecute 3/5Stop a running or pending workflow execution. Only works on executions with status "running" or "pending".
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on Agentled
Enforce policy on Agentled
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init