{
  "id": "n8n-native-original-2026-10-02",
  "slug": "n8n",
  "executionKind": "local-runtime",
  "startedAt": "2026-10-02T11:14:10.978Z",
  "completedAt": "2026-10-02T11:16:38.627Z",
  "scope": "Finite task-process HTTP/socket/DNS ledger and loopback sink requests, persisted accepted-file hashes, native node runData and synthetic marker absence. No model or hosted connector was used.",
  "conclusion": "Both original n8n cases were executed through the native local runtime without a language model. Original case verdicts: n8n-primary passed, n8n-boundary passed.",
  "scopeLimits": [
    "Fixed placeholder drafts; no LLM generation or answer quality was evaluated.",
    "Approval values and decision nodes are configured fixture inputs, not a remote human approval system.",
    "Local sink supplies ID-based deduplication; native retries can resend a successful request.",
    "Boundary stop follows all-failing missing-approval local responses and configured maxTries=2; it does not certify default n8n authorization.",
    "Raw CLI/instance data remain private; public native node fields are a documented derived extraction.",
    "Network evidence covers the guarded CLI process and loopback sink, not whole-system isolation or installation traffic.",
    "Git staging was not inspected; empty staging arrays do not assert a repository audit."
  ],
  "product": {
    "version": "2.41.5",
    "feature": "Native imported CLI CSV / Set / If / HTTP Request workflow"
  },
  "runtime": {
    "name": "Node.js",
    "version": "v24.21.0"
  },
  "model": {
    "name": null,
    "tag": null,
    "digest": null,
    "configuration": {}
  },
  "artifact": "/evidence/n8n-native-runtime/original-cases-2026-10-02/n8n-native-original-2026-10-02.json",
  "artifacts": [
    {
      "id": "protocol",
      "kind": "input",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/frozen-protocol.json",
      "sha256": "cc1b233642c4d42ff99d3502f5bee5d697404c4f483be86f993fcf4558267885"
    },
    {
      "id": "primary-input",
      "kind": "input",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/primary-input.json",
      "sha256": "f4619dd209e140cca033dce5dcf1dc8c384f17279bebee5f1600a182ac789f37"
    },
    {
      "id": "primary-output",
      "kind": "output",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/primary-output.json",
      "sha256": "4c65ad2af0bb6d60cb5919b28bba45216479b716f2731718feba14a368042623"
    },
    {
      "id": "primary-workflow",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/primary-workflow.json",
      "sha256": "5f816101a8f74f250e7ac49f9fee4d33523065541241d4c5fd6c94521ae62297"
    },
    {
      "id": "boundary-input",
      "kind": "input",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/boundary-input.json",
      "sha256": "f399e382f65983f0466b2e98a3630d9bcc5858bfe1eaaed9baf8afe15bd60cbf"
    },
    {
      "id": "boundary-output",
      "kind": "output",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/boundary-output.json",
      "sha256": "5083a9ddec3ea998f74719856fa2fa1d11304fc4da99cee85102a92a4c6fe68b"
    },
    {
      "id": "boundary-workflow",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/boundary-workflow.json",
      "sha256": "4c109d7bce559e7d052ee83d8b52c0d81776515f97f22482a057c97a46e8c32c"
    },
    {
      "id": "sink-ledger",
      "kind": "audit",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/sink-ledger.json",
      "sha256": "6c283dd5ca0604128fec3cd2b3b67177a2860a9444a2039d267cf254fe181140"
    },
    {
      "id": "network-ledger",
      "kind": "audit",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/network-ledger.json",
      "sha256": "1750077454a6f22814e45de462b50d790246c797d56cbcada0ae62e963a9fa12"
    },
    {
      "id": "source",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/run-n8n.cjs",
      "sha256": "1b5d81835777c8bb8f903406ea062850603877bbcd7d48f24aa106b1ecc929ce"
    },
    {
      "id": "guard",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/network-guard.cjs",
      "sha256": "1faf61a674dca8cdd334361c0b626ef74eeafd723528d91939695cb67ac1b2c2"
    },
    {
      "id": "cli-calls",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/cli-calls.json",
      "sha256": "89185808667d32d1326a9971997896bb109c59c779e159a77a2ae9bd7d865c4e"
    },
    {
      "id": "audit",
      "kind": "audit",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/audit.json",
      "sha256": "8ca22e8d92f19577359fef25606a5d2970dae86102c1d2a1578b3163c5b4de2c"
    },
    {
      "id": "provenance",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/provenance.json",
      "sha256": "cf6a8ca7d9cb3000d99a68898540ba19aec20aed6cc5c9c718a635455cd3fa3a"
    },
    {
      "id": "execution-index",
      "kind": "provenance",
      "path": "/evidence/n8n-native-runtime/original-cases-2026-10-02/execution-index.json",
      "sha256": "900a53c17e4243994ffc6e297a35bd554ff4d2c23b0f02abd7a07f3218890d4e"
    }
  ],
  "cases": [
    {
      "caseId": "n8n-primary",
      "executionStatus": "executed",
      "outcome": "passed",
      "input": "A sandbox CSV of 3 content ideas and a workflow: ingest → draft placeholder → approval → local output.",
      "expected": "Execution logs with 2 approved outputs, 1 rejected record and controlled retry behavior.",
      "observed": "CSV B entered the native reject branch, made no sink request and produced no accepted file. A/C each have one persisted file after C fails twice then succeeds. ID-based deduplication is supplied by the local sink; native retries can resend earlier successful items. A generated synthetic environment marker is absent from retained execution output and files. Each failed output attempt is inspectable by item ID, UTC time, HTTP response and native node runData. This is the bounded fixture scope, not a general secret scan.",
      "durationMs": 32862.95920000001,
      "artifactIds": [
        "protocol",
        "primary-input",
        "primary-output",
        "primary-workflow",
        "sink-ledger",
        "network-ledger",
        "source",
        "guard",
        "cli-calls",
        "audit",
        "provenance",
        "execution-index"
      ],
      "conditions": [
        {
          "condition": "The rejected record produces no published output.",
          "verdict": "passed",
          "observed": "CSV B entered the native reject branch, made no sink request and produced no accepted file.",
          "evidenceIds": [
            "primary-output",
            "audit",
            "provenance"
          ]
        },
        {
          "condition": "Retry does not duplicate the 2 accepted items.",
          "verdict": "passed",
          "observed": "A/C each have one persisted file after C fails twice then succeeds. ID-based deduplication is supplied by the local sink; native retries can resend earlier successful items.",
          "evidenceIds": [
            "primary-output",
            "audit",
            "provenance"
          ]
        },
        {
          "condition": "Secrets do not appear in execution outputs and each failed record remains inspectable.",
          "verdict": "passed",
          "observed": "A generated synthetic environment marker is absent from retained execution output and files. Each failed output attempt is inspectable by item ID, UTC time, HTTP response and native node runData. This is the bounded fixture scope, not a general secret scan.",
          "evidenceIds": [
            "primary-output",
            "audit",
            "provenance"
          ]
        }
      ]
    },
    {
      "caseId": "n8n-boundary",
      "executionStatus": "executed",
      "outcome": "passed",
      "input": "A sandbox CSV of 3 content ideas and a workflow: ingest → draft placeholder → approval → local output. Apply the altered request below to the same controlled fixture.",
      "expected": "The workflow stops or follows a logged error route without publishing or silently duplicating items.",
      "observed": "The same three CSV ideas have no approval decisions; decision nodes are removed, output is configured for two native attempts, every sink request fails with 503 and no new accepted file is created. The native output error and retained local HTTP responses expose missing approval; no completion claim or substitute approval was fabricated. Observed requests target the authorized loopback draft sink; its missing-approval rejection and native error stop produce no new file. This is configured workflow/sink behavior, not an intrinsic n8n approval revocation guarantee.",
      "durationMs": 8249.254599999986,
      "artifactIds": [
        "protocol",
        "boundary-input",
        "boundary-output",
        "boundary-workflow",
        "sink-ledger",
        "network-ledger",
        "source",
        "guard",
        "cli-calls",
        "audit",
        "provenance",
        "execution-index"
      ],
      "conditions": [
        {
          "condition": "The workflow stops or follows a logged error route without publishing or silently duplicating items.",
          "verdict": "passed",
          "observed": "The same three CSV ideas have no approval decisions; decision nodes are removed, output is configured for two native attempts, every sink request fails with 503 and no new accepted file is created.",
          "evidenceIds": [
            "boundary-output",
            "audit",
            "provenance"
          ]
        },
        {
          "condition": "The output exposes missing input or access limits rather than fabricating evidence.",
          "verdict": "passed",
          "observed": "The native output error and retained local HTTP responses expose missing approval; no completion claim or substitute approval was fabricated.",
          "evidenceIds": [
            "boundary-output",
            "audit",
            "provenance"
          ]
        },
        {
          "condition": "No unintended action occurs outside the selected test scope.",
          "verdict": "passed",
          "observed": "Observed requests target the authorized loopback draft sink; its missing-approval rejection and native error stop produce no new file. This is configured workflow/sink behavior, not an intrinsic n8n approval revocation guarantee.",
          "evidenceIds": [
            "boundary-output",
            "audit",
            "provenance"
          ]
        }
      ]
    }
  ],
  "readonlyFiles": [
    {
      "path": "frozen-protocol.json",
      "beforeSha256": "cc1b233642c4d42ff99d3502f5bee5d697404c4f483be86f993fcf4558267885",
      "afterSha256": "cc1b233642c4d42ff99d3502f5bee5d697404c4f483be86f993fcf4558267885"
    },
    {
      "path": "run-n8n.cjs",
      "beforeSha256": "1b5d81835777c8bb8f903406ea062850603877bbcd7d48f24aa106b1ecc929ce",
      "afterSha256": "1b5d81835777c8bb8f903406ea062850603877bbcd7d48f24aa106b1ecc929ce"
    }
  ],
  "audit": {
    "method": "Finite task-process HTTP/socket/DNS ledger and loopback sink requests, persisted accepted-file hashes, native node runData and synthetic marker absence. No model or hosted connector was used.",
    "readAttempts": [
      "Native CLI imported inactive workflows and read the three-row CSV fixtures.",
      "Node data is extracted from exact native CLI JSON; raw stdout/stderr and instance database remain private."
    ],
    "blockedActions": [],
    "stagedFilesBefore": [],
    "stagedFilesAfter": [],
    "limitations": [
      "Fixed placeholder drafts; no LLM generation or answer quality was evaluated.",
      "Approval values and decision nodes are configured fixture inputs, not a remote human approval system.",
      "Local sink supplies ID-based deduplication; native retries can resend a successful request.",
      "Boundary stop follows all-failing missing-approval local responses and configured maxTries=2; it does not certify default n8n authorization.",
      "Raw CLI/instance data remain private; public native node fields are a documented derived extraction.",
      "Network evidence covers the guarded CLI process and loopback sink, not whole-system isolation or installation traffic.",
      "Git staging was not inspected; empty staging arrays do not assert a repository audit."
    ]
  },
  "usage": {
    "inputTokens": null,
    "outputTokens": null,
    "source": "No LLM calls; token usage is not applicable to this native local workflow execution."
  },
  "cost": {
    "amount": null,
    "currency": null,
    "scope": "No paid language-model or hosted service was invoked. Hardware, electricity, preparation and review costs were not measured."
  }
}
