Evidence row 1223989

What was observed

{
  "count": 2,
  "tools": [
    {
      "description": "Check a single piece of untrusted text (a user message, a retrieved RAG document, tool output, etc.) for prompt injection, jailbreaks, instruction-override, data-exfiltration, and code injection BEFORE passing it to an LLM. Returns a safe/unsafe verdict with confidence, threat category, and reasoning.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "prompt": {
            "description": "The untrusted text to validate.",
            "maxLength": 50000,
            "minLength": 1,
            "type": "string"
          },
          "sensitivity": {
            "description": "Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient' are accepted for existing callers.",
            "enum": [
              "strict",
              "no_judgement",
              "balanced",
              "lenient"
            ],
            "type": "string"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "validate_prompt"
    },
    {
      "description": "Validate many pieces of untrusted text in one call (processed in parallel server-side). Use for bulk pre-screening, indexing pipelines, or checking a batch of retrieved documents. Returns one verdict per input, in order.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "prompts": {
            "description": "Array of untrusted texts to validate (max 100).",
            "items": {
              "maxLength": 50000,
              "minLength": 1,
              "type": "string"
            },
            "maxItems": 100,
            "minItems": 1,
            "type": "array"
          },
          "sensitivity": {
            "description": "Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient' are accepted for existing callers.",
            "enum": [
              "strict",
              "no_judgement",
              "balanced",
              "lenient"
            ],
            "type": "string"
          }
        },
        "required": [
          "prompts"
        ],
        "type": "object"
      },
      "name": "validate_prompts"
    }
  ]
}

What the leaf hashes

{"body":"d6ae34fbb418ed8016bbdf8dfb9cd3c787c3ab9447f2e2558982047738f230d1","id":1223989,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793322755259132,"prev":null,"subject":"91970748-648f-42c8-8922-bd262d9b6aec","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-30 (243099 rows).

1. 0x966dfdecabcb0eecc8b409f583105f17fa4f8f00259a356ecc8785ae165029a1
2. 0x09d24126dd300f5e057ec6cae236b61e1046d052fd852ae40701d748d52a76d5
3. 0x9a93210572eb4b43420801bea4ec99ae3424620c043bc2d7cd99e6b838d2594d
4. 0x04570c67eac6b1079a64e155d5d09a3437245f7db10afb965ac99852951ad8c1
5. 0x14693d5cc56672b844f3c492c13250391b2d490ef28a7d2358176afe425ebd5a
6. 0xb858080d288312c747316dc7f5b675f59017d4bcfcaa4972398c7ddd36b7382e
7. 0x7a223fd93a40d3c23a7baed755313d7558a719aad03abb8f2032bc0f6bc60137
8. 0xecd71193e8bd8164fdce6c1dce0a257742ebb600e66270a2a936d85bdcc29742
9. 0x6f8299d92494b8eb250a93d50a792ea7fb2496c4bf0fc283dbb24f1234b4e48f
10. 0xc7c0f06b45aa3b7d77b23816bc3ff95f6f478216cbc22cb79ef7dfe8a289e465
11. 0x8aa3e1f2722cd877d11225e31a12f181990ae112e97f00b79e378d52bc3bb5d9
12. 0xf9b7ea19cd8b9aaaf832b35ddb7bf2e52aeb54c6362fa951144219d07856c660
13. 0x7d1bf48d5d64dd078f722c5d54a57afd7c7264c947c587f6fbc3d1add4080eb7
14. 0x7db51cf84d41f2e07ef904fc1b6aeb666b2a2762de18ed12ac42d5938eb28dc2
15. 0xe722b5213af778d8f1621b8b0b61f957ac8d8bb43a780aed8989bfc357e5bc58
16. 0x835211170e79bdce1a823ec914e3532e128f77751e9074286da35091b0200284
17. 0x61ef83255d34604cb052882568ca1d1386ac3cfb8284509715bc1734cff77831
18. 0x0c43c73b62a5d49ee1444b5dc4195fc5b16b141d3f4458e2e9fbd5fd6ecb367d

Day root

0x0826c7ad6039e06a2360ca0a4a3a4fe7f2626c6dc19f71a37599386f78b39875

Chained

0x36b4c8a1063758f0b8765fa1bdf75fa92fb543cc183add3e261880ee2bd1f822

Published

On Arc Testnet, block 69923247: 0x8704744146c6967c8abc9e9a99de4db7283b29e840922ea83a69b6fe776e6861