{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "1914",
  "slug": "the-attacker-is-now-an-agent",
  "edition": "2026-11-22T00",
  "url": "https://hangingcontext.com/stories/2026-11-22/the-attacker-is-now-an-agent/",
  "newsroom": "artificial-intelligence",
  "beat": "policy",
  "newsroom_title": "Artificial Intelligence",
  "angle": "Offensive AI agents are now the attacker — the same frameworks defenders use, turned around",
  "headline": "The attacker is now an agent — and the frameworks defenders use, turned around",
  "dek": "An Entra application minted three accounts and disabled them five minutes later. A medical imaging tool was exploited by agents in the wild. The defence on offer: inventories, runtime checks, and a kill switch.",
  "published_at": "2026-11-22T00:49:50Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 3 Manifests",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 3,
  "publishers": [
    "abnormal-security-publishing",
    "straiker-blog",
    "zeropath-blog"
  ],
  "sources": [
    "abnormal-security-publishing",
    "straiker-blog",
    "zeropath-blog"
  ],
  "distinct_source_count": 3,
  "key_facts": [
    {
      "text": "An operator abused an Entra application to create three accounts and obtain tokens for an internal business API, then disabled each account roughly five minutes after creating it.",
      "cites": [
        {
          "claim_ids": [
            "1795225696207702589",
            "1795225696212702599"
          ],
          "manifest_id": "1795225313709697886"
        }
      ],
      "self_reported": false
    },
    {
      "text": "MONAI Label carries a path traversal flaw, CVE-2026-133968, with a CVSS score of 9.8, exploited in the wild since September 2026.",
      "cites": [
        {
          "claim_ids": [
            "1795303726255967629",
            "1795303726256967630",
            "1795303726256967631"
          ],
          "manifest_id": "1795303503672962741"
        }
      ],
      "self_reported": false
    },
    {
      "text": "The fix for the MONAI Label flaw exists only on the project's main branch, merged on October 19, 2026, and has not shipped in a packaged release.",
      "cites": [
        {
          "claim_ids": [
            "1795303726257967632",
            "1795303726262967639"
          ],
          "manifest_id": "1795303503672962741"
        }
      ],
      "self_reported": false
    },
    {
      "text": "GPT-6.2 models meet the 'Critical' threshold for cybersecurity under OpenAI's Preparedness Framework.",
      "cites": [
        {
          "claim_ids": [
            "1795232800068726655"
          ],
          "manifest_id": "1795232417686725796"
        }
      ],
      "self_reported": false
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "Three accounts, five minutes",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795225696203702588",
                "1795225696207702589",
                "1795225696210702596",
                "1795225696212702598",
                "1795225696212702599",
                "1795225696210702593"
              ],
              "manifest_id": "1795225313709697886"
            }
          ],
          "markdown": "In a US financial-services tenant, an operator abused an existing Microsoft Entra application to create three accounts and obtain tokens for an internal business API, according to Abnormal Security. The application held an Exchange Online role, full_access_as_app, granting access to mailboxes across the tenant. Sign-in attempts arrived six to nine seconds after each account was created, using the resource owner password credentials grant, and the application disabled each account roughly five minutes after creating it. Entra recorded the application's service principal as the initiator of each directory action, with no signed-in user behind it. It is the shape of an attack run by software, not a person at a keyboard."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795225696220702611",
                "1795225696208702592",
                "1795225696218702608",
                "1795225696219702609",
                "1795225696215702604",
                "1795225696214702602"
              ],
              "manifest_id": "1795225313709697886"
            }
          ],
          "markdown": "Abnormal assesses with moderate confidence that the activity is linked to ARTEX and AntiFox tooling. AntiFox is a fork of ARTEX, an agentic offensive framework. The evidence does not establish how the operator first came to control the application, and the application's original business purpose could not be verified. That honesty matters. What is documented is the pattern, and Abnormal publishes a Sigma correlation rule for detecting the create-sign-in-disable sequence. One host involved in the activity was also seen targeting two other organisations within days."
        }
      ]
    },
    {
      "heading": "Agents exploiting a medical tool",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795303726255967629",
                "1795303726259967635",
                "1795303726260967637",
                "1795303726256967630",
                "1795303726256967631",
                "1795303726260967636",
                "1795303726263967641"
              ],
              "manifest_id": "1795303503672962741"
            }
          ],
          "markdown": "The same pattern, agents doing the exploiting, showed up in medical imaging software. MONAI Label, a widely used annotation tool, carries a path traversal flaw, CVE-2026-133968, with a CVSS score of 9.8, exploited in the wild since September 2026. Autonomous Cairn agents reached arbitrary file write about 11 minutes after starting API mapping. A campaign targeted university networks in East Asia. The attackers used the traversal to write a Python reverse shell into sitecustomize.py, a file Python imports automatically at interpreter start. Authentication is off by default in MONAI Label, so in many deployments the endpoint is reachable by unauthenticated clients."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795303726257967632",
                "1795303726261967638",
                "1795303726262967639",
                "1795303726265967643"
              ],
              "manifest_id": "1795303503672962741"
            }
          ],
          "markdown": "The fix exists, but only just. It was merged into the project's main branch on October 19, 2026, and at the time of writing had not shipped in a packaged release. The advisory recommends withholding the ANNOTATOR role from untrusted users. Amazon's CISO, CJ Moses, characterized the operators as suspected Chinese spies, based on script timestamps and prompts: a suspicion, not a proven attribution. The lesson for a technology executive is not about one tool. It is that the attacker is now an agent, the defender's tools can be turned around, and the window between a fix being merged and a fix being installed is where the damage happens."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795303726258967633",
                "1795303726258967634",
                "1795303726262967639"
              ],
              "manifest_id": "1795303503672962741"
            }
          ],
          "markdown": "The flaw itself is mundane, which is the point. The vulnerable entry point is the image parameter of PUT /datastore/image, and the LocalDatastore.add_image function fails to verify that resolved paths remain within the datastore directory. The fix, which uses os.path.commonpath to keep destination paths inside the allowed base directory, is what has not shipped yet."
        }
      ]
    },
    {
      "heading": "The defence on offer: inventory, checks, and a kill switch",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795232800068726655",
                "1795232800071726657"
              ],
              "manifest_id": "1795232417686725796"
            }
          ],
          "markdown": "The labs' answer, as Straiker sets it out for security teams working with OpenAI's GPT-6.2 models, starts with knowing what you have: maintain a full inventory of AI agents, including their models, tools and permissions. The models themselves meet the Critical threshold for cybersecurity under OpenAI's Preparedness Framework — the highest level the framework assigns — which is why the advice is about operating them, not about trusting them."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795232800071726658",
                "1795232800072726659",
                "1795232800073726660"
              ],
              "manifest_id": "1795232417686725796"
            }
          ],
          "markdown": "The rest of the advice is procedural. Security testing should be performed whenever models, prompts or agent configurations change, and runtime security tools should evaluate prompts and tool calls to block malicious activity. And when an agent does go wrong, there should be an Agentic Kill Switch to isolate it during the incident. None of this stops an operator abusing an Entra application or an agent exploiting a medical tool. It is a way of making sure that when it happens, someone notices fast and can cut the agent off."
        }
      ]
    }
  ],
  "unresolved": [
    "How the operator first came to control the Entra application, and what its original business purpose was.",
    "When a packaged MONAI Label release carrying the fix will ship.",
    "Whether the operators behind the MONAI Label campaign are who Amazon's CISO suspects them to be.",
    "Whether runtime checks and kill switches get adopted beyond the teams that publish guidance about them."
  ],
  "decision_card": {
    "not_for": [
      "Treating a suspicion about who ran a campaign as proven attribution",
      "Assuming a merged fix is an installed fix"
    ],
    "useful_for": [
      "Checking whether your tenant has over-privileged applications an agent could abuse",
      "Seeing how quickly an agent can go from a public flaw to root access"
    ],
    "compare_against": [
      "Other agentic offensive frameworks and how they are detected",
      "The time between a fix being merged and a packaged release shipping",
      "Your own Entra application permissions against the least-privilege standard"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-11-22T00"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1795225313709697886",
    "1795303503672962741",
    "1795232417686725796"
  ],
  "manifests": [
    {
      "title": "ARTEX in the Tenant: How an Agentic Offensive Framework Abused an Entra Application to Mint Disposable Accounts",
      "source_url": "https://abnormal.ai/blog/artex-antifox-entra-application-abuse",
      "manifest_id": "1795225313709697886",
      "source_name": "abnormal-security-publishing",
      "published_date": "2026-11-20"
    },
    {
      "title": "Brief Summary: MONAI Label CVE-2026-133968 Path Traversal to Remote Code Execution, Exploited by AI Agents",
      "source_url": "https://zeropath.com/blog/cve-2026-133968-monai-label-path-traversal-rce",
      "manifest_id": "1795303503672962741",
      "source_name": "zeropath-blog",
      "published_date": "2026-11-20"
    },
    {
      "title": "What Security Teams Need to Know About OpenAI's GPT-6.2 Astra and Sol",
      "source_url": "https://straiker.ai/blog/gpt-6-2-astra-sol-agent-security",
      "manifest_id": "1795232417686725796",
      "source_name": "straiker-blog",
      "published_date": "2026-11-20"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1795225313709697886",
      "1795303503672962741",
      "1795232417686725796"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. Existing 72 Hour Agent Demo keys keep their issued limits. New keys require email OTP verification. An existing demo key lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1795225313709697886",
      "all": "for id in 1795225313709697886 1795303503672962741 1795232417686725796; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-11-22/the-attacker-is-now-an-agent/",
    "json": "https://hangingcontext.com/stories/2026-11-22/the-attacker-is-now-an-agent/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-11-22/the-attacker-is-now-an-agent/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-11-22T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/new-models-new-price-tags/",
      "headline": "OpenAI split its flagship in two. Smaller labs priced by the second and the token.",
      "slug": "new-models-new-price-tags"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/agents-move-into-the-back-office/",
      "headline": "Agents move into the back office: buying, shipping, and the data underneath",
      "slug": "agents-move-into-the-back-office"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/proving-who-did-the-work/",
      "headline": "When agents do the work, proving who did it becomes the product",
      "slug": "proving-who-did-the-work"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/ai-spend-gets-a-budget/",
      "headline": "AI spend is now big enough to need its own budget discipline",
      "slug": "ai-spend-gets-a-budget"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Ask what Synorb covers",
    "text": "The MCP tool synorb-stream-search answers questions like \"do you have this publisher?\" without using any Manifest allowance.",
    "cta": {
      "label": "Connect and ask",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-11-22/the-attacker-is-now-an-agent/"
  }
}
