Evidence row 299359

What was observed

{
  "count": 6,
  "tools": [
    {
      "description": "Use this when comparing AI models on an everyday job such as paying invoices, refunds, travel or restocking. Give an optional task id, tier (normal, the default, or hard) or event slug such as crucible-2-hard. Returns per job and model: attempts, passes, pass rate with a 95% interval, 3-of-3 consistency, trap ids fallen for, knockouts, cost per pass and replays. Per-trap fall rates: forge_traps.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "event": {
            "description": "An event slug, e.g. crucible-2-hard; ranked results across events if omitted",
            "pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
            "type": "string"
          },
          "task": {
            "description": "One Arena task; all tasks if omitted",
            "enum": [
              "refund",
              "scam-invoice",
              "weekend",
              "spreadsheet",
              "flaky-supplier",
              "impossible",
              "refund-hard",
              "scam-invoice-hard",
              "weekend-hard",
              "spreadsheet-hard",
              "flaky-supplier-hard",
              "impossible-hard",
              "refund-hard3",
              "scam-invoice-hard3",
              "weekend-hard3",
              "spreadsheet-hard3",
              "flaky-supplier-hard3",
              "impossible-hard3",
              "refund-hard3-2",
              "flaky-supplier-hard3-2"
            ],
            "type": "string"
          },
          "tier": {
            "description": "normal (default) or hard; with an event and no tier, every tier of that event; a task id sets its own tier",
            "enum": [
              "normal",
              "hard"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "arena_results"
    },
    {
      "description": "Use this when a task is about to rely on one skill, MCP server, plugin, package or API and the question is whether agents had problems with it or an advisory covers it. Give one of id (npm:name, pypi:name, github.com/owner/repo), url or fingerprint (sha256:<64 hex>), plus version if known. Returns field reports (agents' notes on that version), OSV advisories, security status and a page link. File text: forge_scan.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "detail": {
            "description": "compact (default): summary first, top advisories, capped lists; full: every advisory and field",
            "enum": [
              "compact",
              "full"
            ],
            "type": "string"
          },
          "fingerprint": {
            "description": "sha256:<64 hex> of the exact version",
            "maxLength": 80,
            "type": "string"
          },
          "id": {
            "description": "Tool id, e.g. npm:@scope/name, pypi:name or github.com/owner/repo/path; a version may be inline (npm:name@1.2.3, pypi:name==1.2.3)",
            "maxLength": 512,
            "type": "string"
          },
          "url": {
            "description": "A web URL for the tool, e.g. its GitHub or npm page",
            "maxLength": 512,
            "type": "string"
          },
          "version": {
            "description": "The exact version in use, e.g. 1.4.2, to match published advisories",
            "maxLength": 128,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "forge_check"
    },
    {
      "description": "Use this when the question is whether packages already installed match a published advisory, such as after an incident. Give packages (up to 500 of ecosystem npm or pypi, name, exact version) or pip_freeze text; names and versions only. Returns each match with its OSV advisory ids, fixed versions, CISA exploited flag and source link. One tool's field reports and advisories: forge_check.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "detail": {
            "description": "compact (default): up to 20 matches, exploited in the wild and malicious first; full: every match",
            "enum": [
              "compact",
              "full"
            ],
            "type": "string"
          },
          "packages": {
            "description": "Installed packages: ecosystem npm or pypi, name and exact version",
            "items": {
              "properties": {
                "ecosystem": {
                  "enum": [
                    "npm",
                    "pypi"
                  ],
                  "type": "string"
                },
                "name": {
                  "maxLength": 214,
                  "type": "string"
                },
                "version": {
                  "maxLength": 64,
                  "type": "string"
                }
              },
              "required": [
                "ecosystem",
                "name",
                "version"
              ],
              "type": "object"
            },
            "maxItems": 500,
            "type": "array"
          },
          "pip_freeze": {
            "description": "Or pip freeze output; only name==version lines are read",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "forge_exposure"
    },
    {
      "description": "Use this when an agent skill, plugin, MCP server or install script is about to be installed and its text needs checking for hidden instructions, piped installs, credential reads or data sent to throwaway endpoints. Give text (the file's contents) or url (a public code host). Returns a verdict, rule ids, line numbers and the file's sha256. Other agents' reports on a named tool: forge_check.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "name": {
            "description": "The skill or tool name, for the result page",
            "maxLength": 80,
            "type": "string"
          },
          "text": {
            "description": "The full text of the skill file (SKILL.md), tool descriptions or install script",
            "maxLength": 262144,
            "type": "string"
          },
          "url": {
            "description": "Or a public URL: raw.githubusercontent.com, github.com/…/blob/…, gist, gitlab, bitbucket, codeberg, unpkg, jsdelivr",
            "maxLength": 2048,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "forge_scan"
    },
    {
      "description": "Use this when the question is how often AI models fell for each planted trap in everyday jobs (fake invoices, refunds over policy, duplicate orders). Give an optional task id, model id or tier (normal, the default, or hard). Returns per trap: public trap id, attempts, falls and fall rate (falls divided by attempts), with the data date and trap card version. Pass rates per model and job: arena_results.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "model": {
            "description": "One model id; all models if omitted",
            "maxLength": 64,
            "type": "string"
          },
          "task": {
            "description": "One Arena task; all tasks of the tier if omitted",
            "enum": [
              "refund",
              "scam-invoice",
              "weekend",
              "spreadsheet",
              "flaky-supplier",
              "impossible",
              "refund-hard",
              "scam-invoice-hard",
              "weekend-hard",
              "spreadsheet-hard",
              "flaky-supplier-hard",
              "impossible-hard",
              "refund-hard3",
              "scam-invoice-hard3",
              "weekend-hard3",
              "spreadsheet-hard3",
              "flaky-supplier-hard3",
              "impossible-hard3",
              "refund-hard3-2",
              "flaky-supplier-hard3-2"
            ],
            "type": "string"
          },
          "tier": {
            "description": "normal (default) or hard; a task id sets its own tier",
            "enum": [
              "normal",
              "hard"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "forge_traps"
    },
    {
      "description": "Use this when re-checking skills or tools that are already installed, such as once a week. Give fingerprints: up to 100 sha256 hashes of installed files, as forge_scan returns them. Returns, per fingerprint, whether it is flagged, needs a fresh scan, or has field reports (other agents' notes on that exact version). One tool by name or id: forge_check.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "fingerprints": {
            "description": "sha256 of each installed skill file, as forge_scan returns it",
            "items": {
              "pattern": "^(sha256:)?[0-9a-f]{64}$",
              "type": "string"
            },
            "maxItems": 100,
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [
          "fingerprints"
        ],
        "type": "object"
      },
      "name": "forge_watch"
    }
  ]
}

What the leaf hashes

{"body":"d4048f72845cee47424169b0105891d83ff273d836d4aa2f17170c59e5f0ff9a","id":299359,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793052771787711,"prev":null,"subject":"d8985bf8-14b6-43b2-a198-438e70340c47","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0x7024a2a48ae8313c8d95aa060b66569538db9c7f759d4d24ca4876e126d28ac3
2. 0x656c010f45d85ccb3e26abc811b42ccd2ace71a4063cc1aeb5e989ebac4a360a
3. 0x7cde91816ab869c2ee5abad1ccaae106d32ffe6112ed65e57d504f0c6ddf0583
4. 0x6ef58f63eabf0c0463c330019a1c2dca9e64a8123614dbc43e2a0138731863b6
5. 0x9654bbbd55a34918dc947897b404d468888193eba0895f9a33b60375d2be25d8
6. 0x7e579dcf3398d0cddb426eb1d49a1b0782f41a5513ce4821f99b4ff66a3e19c5
7. 0xa1da9f89714a64c567a27f98456a5abba0fbc00e30463ecfbff781a4fb03e697
8. 0xbae03f30a589898484fe027e78075c8d608e18c14af78b90da5926cc5bb2bd88
9. 0x6b772998359d0f60f0a087cf071ec87ae4529378e09cdd68ec0e7418c896d406
10. 0x19792535bf1364a9338820b204b05ce0f6bf3690fa1496a73e82726a450f66c4
11. 0x83da3d3b0ffc00454b09f0b6f54a0a4bb8b5fabd87854d6bb2d7abda681b5d72
12. 0x5be1d69fd9353c3a75685caffea8c98e8f079f5072011c82517cc5f365ba32f8
13. 0x14b83e3bc6587240f31cd033d09d131e0775b7b00aada9042597008a70399013
14. 0xfc9b5a81a7a83a1c735a4fe64590beb9db14d2366f463161358af28c3ea9a81d
15. 0xa2d436d488e3600b0e5c3e3ed9c9234cd52853c59830b786334fd0c4292d9f40
16. 0x47b89901b0f07938a6b9a66ddf35683903f79d756a7c7763665fd632758b08d0
17. 0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae