CVE-2026-123019

waiting for further signalsZero needs more public information before it can validate it.

GHSA-w66p-3ghr-2qhf ↗EUVD-2026-117415 ↗

no check availablenot proven exploitable
cve.orgpublic pocExploit code has been published by someone. Source signals can also carry a PoC (Proof of Concept).kevAttacks confirmed in the real world.
eosphoros-ai DB-GPT 0.8.0; 0.8.1; 0.8.2
ETK-2026-3624Zero's internal tracking ID, independent of the CVE number., permanent identifier
9h 31msince last run
30mAI analysisAnalysis: how long the AI spent reversing this signal.
timeline
0 = cve.org publication
trigger signal (cve.org) +0hwaiting for further signals+1h20m
0
+2h
+4h
+6h
+8h
+10h
+12h

description

DB-GPT versions through 0.8.2 are affected in the HuggingFace Adapter. A remote attacker may cause untrusted remote code to be loaded if they can influence the trust_remote_code setting used by the adapter.

mitigation

Do not enable trust_remote_code for untrusted models, and prevent untrusted users or requests from controlling this setting. Restrict access to the HuggingFace Adapter until the project publishes a corrected release.

check
no
exploit
no
automationDeterministic: a check that runs on its own, the same request on every target. Contextual: an agentic technique that needs to be applied per target, for bugs that depend on contextual flows.
contextual
auth requiredWhether an attacker needs an account first, based on the CVSS vector's Privileges Required.
no
EPSSEstimate of the chance this CVE is exploited in the next 30 days. Refreshed daily.
–
agent run time
30m
cve.org record, t = 0The moment cve.org publishes the CVE in full.
2026-11-05 12:00Z
Δ to public pocExploit code has been published by someone. Source signals can also carry a PoC (Proof of Concept).
–
Δ to kevAttacks confirmed in the real world.
–

outcome

Contextual, not validated: no deterministic check could cover this one, and no technique passed our review.

source signals

Public signals that triggered or updated the pipeline. These are inputs for the deltas above.

  1. 2026-11-05 12:00Z
    ghsa: trigger signal, started the run
  2. 2026-11-05 12:00Z

this entry in the feed

GET /api/v1/feed/CVE-2026-123019

{
  "etk_id": "ETK-2026-3624",
  "cve_id": "CVE-2026-123019",
  "display_id": "CVE-2026-123019",
  "ghsa_id": "GHSA-w66p-3ghr-2qhf",
  "euvd_id": "EUVD-2026-117415",
  "status": "published",
  "anchor_state": "anchored",
  "title": "Untrusted code loading in DB-GPT HuggingFace Adapter",
  "summary": "DB-GPT versions through 0.8.2 are affected in the HuggingFace Adapter. A remote attacker may cause untrusted remote code to be loaded if they can influence the trust_remote_code setting used by the adapter.",
  "mitigation": "Do not enable trust_remote_code for untrusted models, and prevent untrusted users or requests from controlling this setting. Restrict access to the HuggingFace Adapter until the project publishes a corrected release.",
  "vendor": "eosphoros-ai",
  "product": "DB-GPT",
  "affected": [
    {
      "affected_notes": [],
      "affected_ranges": [
        "0.8.0",
        "0.8.1",
        "0.8.2"
      ],
      "ecosystem": null,
      "fixed_versions": [],
      "package_name": "DB-GPT",
      "purl": null
    }
  ],
  "cwes": null,
  "cvss_score": 7.3,
  "cvss_src": "cna_vendor",
  "cvss_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L",
  "epss_score": null,
  "epss_percentile": null,
  "epss_asof": null,
  "automation": "contextual",
  "check": false,
  "check_confidence_basis": null,
  "exploit": false,
  "pipeline_minutes": 30.260817166666666,
  "t0_at": "2026-11-05T12:00:20.915000+00:00",
  "signals": {
    "trigger_signal": {
      "at": "2026-11-05T12:00:20.915000+00:00",
      "days": 0,
      "is_lower_bound": false,
      "measured_at": "2026-11-05T12:00:20.915000+00:00",
      "url": "https://github.com/advisories/GHSA-w66p-3ghr-2qhf"
    }
  }
}

published 2026-11-05 12:49Z
last change 2026-11-05 18:56Z

Need the technical details behind an entry?

Every entry here shows what we attempted and when. The technical details, the generated exploit that fired it and the evidence behind the verdict are not public. Tell us about your use case and we’ll get back to you about extended API access.