performance_profile

What performance_profile does on Ruflo

AI agents invoke performance_profile to trigger actions in Ruflo. 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.

Why performance_profile is rated High

Profiling a component or operation requires actively running or instrumenting it, which constitutes execution. The mention of 'native shell timing' strongly suggests shell-level execution is involved. In a multi-agent swarm harness, misuse could trigger unintended operations across agents, warranting high severity. Confidence is slightly reduced because the description is truncated and full behavior is unclear.

From the tool's definition 'Profile specific component or operation' and reference to 'native shell timing' — implies execution of profiling operations against live components/operations in a multi-agent swarm environment

The rule that runs performance_profile safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Ruflo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For performance_profile, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "performance_profile": {
      "limits": [
        {
          "counter": "performance_profile_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about performance_profile