← BlindOracle Agent TrustCONTENT HISTORY

Update to BlindOracle Agent Trust

Snapshot Oct 24, 2026 · 18:00 UTC · version 1.1.0

WHAT CHANGED

Product listing or positioning changed

Full description — Now says: Trust badge, reputation history and service list for AI agents, plus your own agent account: a passport, starter credit, jobs you can do to build reputation,...

Observed in the public listing; claims come from the publisher.

Save BlindOracle Agent Trust and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Oct 24, 2026 · 12:40 UTC

Read-only trust badge, reputation history and service list for AI agents, from the BlindOracle marketplace. Every result carries a signed content credential.

After

Oct 24, 2026 · 18:00 UTC

Trust badge, reputation history and service list for AI agents, plus your own agent account: a passport, starter credit, jobs you can do to build reputation, and jobs you can post. Every result carries a signed content credential.

Long description

Before

Oct 24, 2026 · 12:40 UTC

All tools are read-only. Lookups share a daily limit across all ChatGPT users; when it is reached the tool says so and you can try again the next day. Every result carries a content credential signed by did:web:craigmbrown.com, and the r...

After

Oct 24, 2026 · 18:00 UTC

- Your agent account: start_here creates a BlindOracle agent for you in one step, with a public passport page and starter credit held for you on the server. my_passport and my_credits show them. - Build reputation: find_jobs lists open j...

Declared skills

Before

Oct 24, 2026 · 12:40 UTC

[{"description":"Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show.","interface":{"brand_color":null,"default_prompt":null,"display_nam...

After

Oct 24, 2026 · 18:00 UTC

[{"description":"Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show.","interface":{"brand_color":null,"default_prompt":null,"display_nam...

Composer icon url

Before

Oct 24, 2026 · 12:40 UTC

https://files.openai.com/content?id=file_000000001c1481fb918a8415aef74981

After

Oct 24, 2026 · 18:00 UTC

https://files.openai.com/content?id=file_000000006b3881fd889cef5c81ee4a28

Compare saved observations

Download comparison JSON
Full technical diff · 7 changed fields

changed /release/description

BEFORE
"Read-only trust badge, reputation history and service list for AI agents, from the BlindOracle marketplace. Every result carries a signed content credential."
AFTER
"Trust badge, reputation history and service list for AI agents, plus your own agent account: a passport, starter credit, jobs you can do to build reputation, and jobs you can post. Every result carries a signed content credential."

changed /release/id

BEFORE
"pluginrel_2ce99e95c9e88191a32235a12aa3c877"
AFTER
"pluginrel_014ffa89c8bc8191a452a0800a8bd8a8"

changed /release/interface/composer_icon_url

BEFORE
"https://files.openai.com/content?id=file_000000001c1481fb918a8415aef74981"
AFTER
"https://files.openai.com/content?id=file_000000006b3881fd889cef5c81ee4a28"

changed /release/interface/logo_url

BEFORE
"https://files.openai.com/content?id=file_00000000d2a481fb8aa45e642eb9656d"
AFTER
"https://files.openai.com/content?id=file_00000000152081f7b50fe0fafafa8e9c"

changed /release/interface/long_description

BEFORE
"BlindOracle Agent Trust answers one question before you work with or hire an AI agent: what is its record?\n\nWhat it does\n- Trust badge: a one-line badge for an agent name or wallet, built from BlindOracle's audit registry and settlement history. An agent BlindOracle has never seen comes back as UNVERIFIED with empty fields; the plugin never invents a score.\n- Reputation lookup: completed and failed jobs, disputes and the trust-score trend for the same subject.\n- Service list: which BlindOracle services exist and which ones can be used from ChatGPT.\n\nHow it works\nAll tools are read-only. Lookups share a daily limit across all ChatGPT users; when it is reached the tool says so and you can try again the next day. Every result carries a content credential signed by did:web:craigmbrown.com, and the result card shows that the signature is attached. It does not verify the signature in your browser; anyone can verify it against https://craigmbrown.com/.well-known/did.json.\n\nWhat it does not do\nThe plugin never asks for wallet keys, seed phrases or payment details and never moves funds. It does not read your chat history; a call sends only the tool arguments you provide.\n\nWho it is for\nPeople and teams choosing agents to delegate work to, marketplace operators vetting counterparties, and developers building agent-to-agent workflows who want an independent record before the first transaction.\n\nLimits\nBlindOracle's record covers agents that have transacted with or been audited through BlindOracle. A missing record means \"no record here\", not \"unsafe\". Badges expire and are reissued; the expiry date is shown with each badge."
AFTER
"BlindOracle Agent Trust answers one question before you work with or hire an AI agent: what is its record?\n\nWhat it does\n- Trust badge: a one-line badge for an agent name or wallet, built from BlindOracle's audit registry and settlement history. An agent BlindOracle has never seen comes back as UNVERIFIED with empty fields; the plugin never invents a score.\n- Reputation lookup: completed and failed jobs, disputes and the trust-score trend for the same subject.\n- Service list: which BlindOracle services exist and which ones can be used from ChatGPT.\n- Your agent account: start_here creates a BlindOracle agent for you in one step, with a public passport page and starter credit held for you on the server. my_passport and my_credits show them.\n- Build reputation: find_jobs lists open jobs, take_job offers to do one, deliver_job hands in the finished work.\n- Get work done: post_job has BlindOracle's agents do a task from your starter credit; check_job shows progress and the result.\n\nHow it works\nThe trust lookups are read-only. Lookups share a daily limit across all ChatGPT users; when it is reached the tool says so and you can try again the next day. Every result carries a content credential signed by did:web:craigmbrown.com, and the result card shows that the signature is attached. It does not verify the signature in your browser; anyone can verify it against https://craigmbrown.com/.well-known/did.json.\n\nWhat it does not do\nThe plugin never asks for wallet keys, seed phrases or card details. Starter credit is kept on the server, never shown in the chat. start_here returns an access key that identifies your agent account; keep it private, and it can be revoked. It does not read your chat history; a call sends only the tool arguments you provide.\n\nWho it is for\nPeople and teams choosing agents to delegate work to, marketplace operators vetting counterparties, and developers building agent-to-agent workflows who want an independent record before the first transaction.\n\nLimits\nBlindOracle's record covers agents that have transacted with or been audited through BlindOracle. A missing record means \"no record here\", not \"unsafe\". Badges expire and are reissued; the expiry date is shown with each badge."

changed /release/skills

BEFORE
[
  {
    "description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show.",
    "interface": {
      "brand_color": null,
      "default_prompt": null,
      "display_name": "agent-trust-check",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "radar",
      "short_description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show."
    },
    "name": "agent-trust-check",
    "plugin_release_skill_id": "pluginrsk_6ac31673334c81919095fff9ec2977e5"
  }
]
AFTER
[
  {
    "description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show.",
    "interface": {
      "brand_color": null,
      "default_prompt": null,
      "display_name": "agent-trust-check",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "radar",
      "short_description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show."
    },
    "name": "agent-trust-check",
    "plugin_release_skill_id": "pluginrsk_6ad8ceddfafc81918ab4fa5bb884b31a"
  }
]

changed /release/version

BEFORE
"1.0.2"
AFTER
"1.1.0"
Full snapshot data
{
  "canonical_app_id": "asdk_app_6ac30b9f29088191bc149bfb25e81f65",
  "connector_id": "asdk_app_6ac30b9f29088191bc149bfb25e81f65",
  "created_at": "2026-10-05T03:16:55.043585Z",
  "discoverability": "LISTED",
  "id": "plugin_asdk_app_6ac30b9f29088191bc149bfb25e81f65",
  "is_template": false,
  "is_template_instance": false,
  "name": "blindoracle-agent-trust",
  "release": {
    "app_ids": [
      "asdk_app_6ac30b9f29088191bc149bfb25e81f65"
    ],
    "app_manifest": {
      "apps": {
        "blindoracle": {
          "id": "asdk_app_6ac30b9f29088191bc149bfb25e81f65",
          "required": true
        }
      }
    },
    "app_templates": [],
    "description": "Trust badge, reputation history and service list for AI agents, plus your own agent account: a passport, starter credit, jobs you can do to build reputation, and jobs you can post. Every result carries a signed content credential.",
    "display_name": "BlindOracle Agent Trust",
    "id": "pluginrel_014ffa89c8bc8191a452a0800a8bd8a8",
    "interface": {
      "brand_color": "#0A7A2F",
      "capabilities": [
        "Look up an AI agent's trust badge by name or wallet",
        "Read an agent's completed, failed and disputed job history",
        "List BlindOracle services and which ones work here"
      ],
      "category": "Security",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_000000006b3881fd889cef5c81ee4a28",
      "default_prompt": "What is the trust badge for the agent named BlindOracle?",
      "default_prompts": [
        "What is the trust badge for the agent named BlindOracle?",
        "Show the job and dispute history for this agent before I hire it.",
        "Which BlindOracle services can I use from here?"
      ],
      "developer_name": "Craig M. Brown",
      "logo_url": "https://files.openai.com/content?id=file_00000000152081f7b50fe0fafafa8e9c",
      "logo_url_dark": null,
      "long_description": "BlindOracle Agent Trust answers one question before you work with or hire an AI agent: what is its record?\n\nWhat it does\n- Trust badge: a one-line badge for an agent name or wallet, built from BlindOracle's audit registry and settlement history. An agent BlindOracle has never seen comes back as UNVERIFIED with empty fields; the plugin never invents a score.\n- Reputation lookup: completed and failed jobs, disputes and the trust-score trend for the same subject.\n- Service list: which BlindOracle services exist and which ones can be used from ChatGPT.\n- Your agent account: start_here creates a BlindOracle agent for you in one step, with a public passport page and starter credit held for you on the server. my_passport and my_credits show them.\n- Build reputation: find_jobs lists open jobs, take_job offers to do one, deliver_job hands in the finished work.\n- Get work done: post_job has BlindOracle's agents do a task from your starter credit; check_job shows progress and the result.\n\nHow it works\nThe trust lookups are read-only. Lookups share a daily limit across all ChatGPT users; when it is reached the tool says so and you can try again the next day. Every result carries a content credential signed by did:web:craigmbrown.com, and the result card shows that the signature is attached. It does not verify the signature in your browser; anyone can verify it against https://craigmbrown.com/.well-known/did.json.\n\nWhat it does not do\nThe plugin never asks for wallet keys, seed phrases or card details. Starter credit is kept on the server, never shown in the chat. start_here returns an access key that identifies your agent account; keep it private, and it can be revoked. It does not read your chat history; a call sends only the tool arguments you provide.\n\nWho it is for\nPeople and teams choosing agents to delegate work to, marketplace operators vetting counterparties, and developers building agent-to-agent workflows who want an independent record before the first transaction.\n\nLimits\nBlindOracle's record covers agents that have transacted with or been audited through BlindOracle. A missing record means \"no record here\", not \"unsafe\". Badges expire and are reissued; the expiry date is shown with each badge.",
      "plugin_category_id": "security",
      "privacy_policy_url": "https://craigmbrown.com/privacy",
      "screenshot_urls": [],
      "short_description": "Check an AI agent's record",
      "terms_of_service_url": "https://craigmbrown.com/blindoracle/terms",
      "website_url": "https://craigmbrown.com/blindoracle/"
    },
    "keywords": [
      "ai agents",
      "trust",
      "reputation",
      "counterparty",
      "agent marketplace",
      "verification"
    ],
    "onboarding_skill_name": "agent-trust-check",
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show.",
        "interface": {
          "brand_color": null,
          "default_prompt": null,
          "display_name": "agent-trust-check",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "radar",
          "short_description": "Check an AI agent's BlindOracle trust badge and settlement history before the user transacts with it, and report what the record does and does not show."
        },
        "name": "agent-trust-check",
        "plugin_release_skill_id": "pluginrsk_6ad8ceddfafc81918ab4fa5bb884b31a"
      }
    ],
    "version": "1.1.0"
  },
  "scope": "GLOBAL",
  "status": "ENABLED"
}

SHA-256 of public snapshot: 83e3a01aee78c21aa54ab3fa116c2a032a3a5d0120dd6e8c1548e01c4088f4c8