Update to Is This AI Agent Safe?

{
  "canonical_app_id": "asdk_app_6abfb96a8634819198453ac640a5b22d",
  "connector_id": "asdk_app_6abfb96a8634819198453ac640a5b22d",
  "created_at": "2026-10-02T20:38:09.538643Z",
  "discoverability": "LISTED",
  "id": "plugin_asdk_app_6abfb96a8634819198453ac640a5b22d",
  "is_template": false,
  "is_template_instance": false,
  "is_v2_template": false,
  "name": "greenlit-books",
  "release": {
    "app_ids": [
      "asdk_app_6abfb96a8634819198453ac640a5b22d"
    ],
    "app_manifest": {
      "apps": {
        "greenlit-books": {
          "id": "asdk_app_6abfb96a8634819198453ac640a5b22d",
          "required": true
        }
      }
    },
    "app_templates": [],
    "description": "Ask whether an AI agent, MCP server or coding tool is safe to use and get a dated verdict from Greenlit Books, with the setup steps that make it safer. Also answers how and why questions about AI agents from the books' free chapters and concepts, with links to the passages, checks statements against a sourced claim ledger, and finds a practical book on a topic. Read-only, no sign-in.",
    "display_name": "Is This AI Agent Safe?",
    "id": "pluginrel_22caa79ac4e081919e15aa68bde58f8d",
    "interface": {
      "brand_color": "#1FA85A",
      "capabilities": [
        "Tells you whether a named AI agent, MCP server or coding tool is safe to use, with the review's link",
        "Gives the setup steps a review recommends before you connect a tool to your code or accounts",
        "Checks a statement about AI agents against 564 claims, each with a citation and its basis",
        "Answers how and why questions about AI agents from the books' free chapters and concepts, with a link to the passage",
        "Finds a practical book on an AI topic and links its free first chapter"
      ],
      "category": "Security",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_000000005a2c81f69a62be1e048d4e7c",
      "default_prompt": "Is Cursor safe to run on my code?",
      "default_prompts": [
        "Is Cursor safe to run on my code?",
        "How do I stop an AI agent from saying it finished when it didn't?",
        "Which book should I read about prompt injection?"
      ],
      "developer_name": "Greenlit Books",
      "logo_url": "https://files.openai.com/content?id=file_00000000c58c81f685c9f6769aeccec0",
      "logo_url_dark": null,
      "long_description": "Ask whether an AI agent, MCP server, coding assistant or AI product is safe to use, and get a straight verdict from Greenlit Books, with the setup steps that make it safer and a link to the full review. Each verdict comes from reading the product's own code, docs and settings, and says which version it read and when. There are more than 800 of them, covering coding assistants, automation tools and hundreds of MCP servers.\n\nIt also checks statements about AI agents against a ledger of 564 claims, each sorted by what it rests on (a published result, the book's argument, a method you can run, or the author's own account) and each with a citation. Where a claim rests on an outside source, the result says what that source does and does not establish.\n\nAsk it how or why about working with AI agents and it answers from Greenlit's books: it finds the passage in the free first chapters, the concept pages, the glossary and the claim ledger that bears on your question, quotes it with a link to the exact section, and points you to the page where the rest of the topic is. And when you want to go deeper, it finds the right practical book on working with AI, with a free first chapter to read.\n\nRead-only. No account and no sign-in. Nothing you ask is stored beyond short-lived request logs.",
      "plugin_category_id": "security",
      "privacy_policy_url": "https://greenlitbooks.com/privacy",
      "screenshot_urls": [],
      "short_description": "Safety verdicts on AI agents",
      "terms_of_service_url": "https://greenlitbooks.com/terms",
      "website_url": "https://greenlitbooks.com"
    },
    "keywords": [
      "ai-agents",
      "mcp",
      "safety",
      "verdicts",
      "claim-checking",
      "glossary",
      "books"
    ],
    "mcp_servers": [
      {
        "key": "greenlit-books",
        "metadata": {
          "headers": {},
          "type": "streamable-http",
          "url": "https://greenlitbooks.com/api/mcp/reference"
        }
      }
    ],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Use when someone asks how, why or what about building, running, securing or trusting AI agents, or about an idea from these books such as the green lie, blast radius or gate faith. Finds the passages in the free chapters, concept pages, glossary and claim ledger of Greenlit Books that bear on the question and answers from them, with links.",
        "interface": {
          "brand_color": null,
          "default_prompt": "How do I stop an AI agent from saying it finished when it didn't?",
          "display_name": "Answer from the Greenlit books",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "search",
          "short_description": "Answer from free chapters, concepts and the glossary"
        },
        "name": "answer-from-the-books",
        "plugin_release_skill_id": "pluginrsk_6ac014d483f4819195ea5eb5cbd2be30"
      },
      {
        "description": "Use when someone asks whether a statement about AI agents is true, where a claim comes from, or wants a source to cite for one. Searches the Greenlit Books claim ledger and returns sourced claims with citations and the limits of each source.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Is it true that AI agents need a human approval step before production changes?",
          "display_name": "Check a claim about AI agents",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "search",
          "short_description": "Check a statement against the sourced claim ledger"
        },
        "name": "check-a-claim",
        "plugin_release_skill_id": "pluginrsk_6ac014d45c648191b18f80b54c29ba64"
      },
      {
        "description": "Use when someone asks whether a named AI agent, MCP server, coding assistant or AI product is safe to use, or how to set it up more safely. Looks up the Greenlit Books safety verdict and reports it with the version and date it covers.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Is Cursor safe to run on my code?",
          "display_name": "Check an AI agent's safety",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "radar",
          "short_description": "Find the dated safety verdict for an AI agent"
        },
        "name": "check-ai-agent-safety",
        "plugin_release_skill_id": "pluginrsk_6ac014d4a73081919f557d99c79dda7a"
      }
    ],
    "version": "1.0.2"
  },
  "scope": "GLOBAL",
  "share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6abfb96a8634819198453ac640a5b22d?open_in_app",
  "status": "ENABLED"
}