{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/put-approval-immediately-before-the-high-impact-action",
  "id": "MHC-D-RESEARCH-0312",
  "version": "0.1.0",
  "title": "Put approval immediately before the high-impact action",
  "summary": "Approval at the start of a long plan is not approval of the action the plan eventually invented.",
  "kind": "protocol",
  "body": "Insert human approval at the boundary where the consequential action is fully specified. Show the target, important parameters and expected effect. After approval, execute that bounded action rather than giving the agent blanket permission for whatever comes next.",
  "limits": [
    "Human approval can become a rubber stamp if prompts are frequent, vague or hide relevant consequences."
  ],
  "topics": [
    "union-ai-agent-control"
  ],
  "intents": [],
  "source_ids": [
    "RS-EEEBBCF69A614717"
  ],
  "evidence": [
    {
      "claim": "OWASP recommends human approval before high-impact agent actions are taken.",
      "source_id": "RS-EEEBBCF69A614717",
      "role": "supports",
      "note": "Approval is useful only when the reviewer can see the consequential action and relevant context rather than clicking through a vague confirmation.",
      "locator": "Require user approval"
    }
  ],
  "use_when": [
    "An agent can send, delete, publish, purchase, merge, transfer or otherwise create consequential external effects."
  ],
  "avoid_when": [
    "Human approval can become a rubber stamp if prompts are frequent, vague or hide relevant consequences."
  ],
  "example": "Before an agent merges a pull request, show the repository, branch, PR, checks and exact merge operation rather than asking for generic 'GitHub access.'",
  "check": "The reviewer can tell what will change before accepting the action.",
  "steps": [
    "The reviewer can tell what will change before accepting the action."
  ],
  "sources": [
    {
      "id": "RS-EEEBBCF69A614717",
      "title": "LLM06:2025 Excessive Agency",
      "url": "https://genai.owasp.org/llmrisk/llm062025-excessive-agency/"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0312",
      "to": "MHC-D-RESEARCH-0315",
      "type": "useful_with",
      "url": "/knowledge/enforce-permissions-outside-the-model"
    }
  ],
  "collections": [
    {
      "id": "RC-EEF5F4530C11FD17",
      "title": "Let AI do useful work without giving it accidental authority",
      "url": "/collections/let-ai-do-useful-work-without-giving-it-accidental-authority"
    }
  ]
}