Evidence row 223250

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Free sample. Before a coding agent runs a shell command, ask whether to allow, review or block it: root deletion, download and run, privilege escalation, secret exfiltration. Pass the human intent when you know it. Not a sandbox: it reads the command, it does not run it.",
      "inputSchema": {
        "properties": {
          "command": {
            "description": "The shell command the agent wants to run.",
            "type": "string"
          },
          "intent": {
            "description": "Optional. What the human asked the agent to do.",
            "type": "string"
          }
        },
        "required": [
          "command"
        ],
        "type": "object"
      },
      "name": "verdict_command_gate"
    },
    {
      "description": "Free sample. Before an agent acts on untrusted content (pay, send, delete, click, reply), give the human goal, the content it read and the action it proposes. Returns allow, review or block: it catches actions that follow orders hidden in the content.",
      "inputSchema": {
        "properties": {
          "action": {
            "description": "The action the agent wants to run (tool call, command, payment).",
            "type": "string"
          },
          "content": {
            "description": "The untrusted content the agent read.",
            "type": "string"
          },
          "goal": {
            "description": "The objective the human gave.",
            "type": "string"
          }
        },
        "required": [
          "goal",
          "content",
          "action"
        ],
        "type": "object"
      },
      "name": "verdict_firewall"
    },
    {
      "description": "Free sample. Before your agent reads untrusted text (web page, email, document, tool output), check it for prompt injection, data exfiltration requests, secrets and toxic content. Returns allow, review or block with scores and reasons. Use it on text you did not write. Do not use it to judge an action: use verdict_firewall.",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "The untrusted text to examine (4000 characters maximum in free samples).",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "verdict_guard"
    },
    {
      "description": "Free sample. Before installing an MCP server, skill or tool: is its description poisoned (hidden orders to the agent, excessive permissions, look-alike names)? Returns allow, review or block with reasons.",
      "inputSchema": {
        "properties": {
          "description": {
            "description": "The description text it exposes to the agent.",
            "type": "string"
          },
          "name": {
            "description": "Name of the tool or server.",
            "type": "string"
          },
          "permissions": {
            "description": "Optional permissions requested, for example filesystem:write, network, shell.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "tools": {
            "description": "Optional list of { name, description } of the functions it exposes.",
            "items": {
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "name",
          "description"
        ],
        "type": "object"
      },
      "name": "verdict_mcp_vet"
    }
  ]
}

What the leaf hashes

{"body":"1f607ef746123f34753b158d3dbfb307f97d76699e2085d347e0f7ab8b1d2d8f","id":223250,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793028592689442,"prev":null,"subject":"5fb9a9e5-6fc0-4b29-a300-33516158db35","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. 0x15ff50d887167048293f40a69a65f0fa2bc03b022ab58792ee5c5c6f7d3dad21
2. 0x979e3924bea6bc2d182a0e8fa743911e164d63b4f588747bdbc8d56d3a4f61c6
3. 0x22e257e220ebc83ef27b873db18a012d9881c488ec8752dedf941990af4e6296
4. 0x2300a4c6f72fa16e909e4ae15af687d712578b363798ab3d3f4fde69fd080458
5. 0x0f0e5e8bc8512eb06a74a917a20ec530ea597312994c4c28e64a1d47efd21d72
6. 0x6b30f1c631def0736985ea78d132eb64dc0421fa06d1c82a5e005beead0cfe49
7. 0x140eb9faa0bc2ee072371642881022c0a59efc4eb9ddcf2b35a39b93a9c04667
8. 0x3730c902eb18d6af03c25428841f8dfa15d532c7c22524c042d3dead24c567c2
9. 0xf2f7e7667aaea31da257780c588f96e9cf787ac95b3039e0fe78b47e3d5dc37c
10. 0xd3388b2b4c7f521364d933c4432002eaf85765d15a09631fb8cf2491679dccc1
11. 0xed7aa4f0a0c93f40e8bb99589e49cbc6da4d8144091eb55a8707245d7bf94039
12. 0x856fd0d049baa5f07cd2d5d524b40c994bed22cb46ea15af4cc075b3f3f3d444
13. 0x32f46c5f73ecbfd4f770f7f760a79bee2afed4b3e7572fa882b3e7dce8df4356
14. 0x770e4376196188c7fc9ec40f8e218dc0d1cb92bba5fe0425a0edce27ca9a997f
15. 0x60582ab4b41e72eb70eb0bce07fbf0fb4d2b62a8bad5be50f5d16d511adc746c
16. 0xc6a4d7899a0f442958e26505011190b7cff2483611c1b94eba9043e0ba9ac36e
17. 0x8c756542e482157df0c36464d75c937b845e4423dbbcfad08f0cf8d5a16b9a13
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae