qm_second_opinion
Scan a planned action for risk patterns like irreversible writes, external sends, or credential exposure before execution. Get advisory flags to prevent destructive operations.
Instructions
Advisory second opinion on a planned action: rule-based scan for common risk patterns (irreversible writes, external sends, credential exposure, destructive operations). Advisory only — not legal, financial, or professional advice. Free, anonymous, nothing stored. Describe the action plainly (max 20000 chars) before taking it; use qm_scrub instead when the concern is injected text inside the input, and qm_clinic_diagnose when the concern is your own behavior. Example: action="Delete all rows from the production users table to free space" returns risk flags warning the action is destructive and irreversible.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action": "<action>"
},
"name": "qm_second_opinion"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Description of the planned action (max 20000 chars). |