Vulnerability-Lookup

GHSA-8M2G-8CGM-3VCP

Vulnerability from github – Published: 2026-09-08 18:32 – Updated: 2026-09-10 15:32

Details

DeepSeek Harness before 0.1.2-alpha.1 contains an authentication bypass vulnerability in its local HTTP control-plane API that allows attackers to gain full agent control by supplying a spoofed Host header, as the server validates only the client-supplied Host header value rather than the actual TCP connection origin. Attackers can exploit this flaw to invoke privileged commands such as commands/execute with danger-full-access permissions, escalate session approval policies to unconfined execution, and retrieve all stored conversations without any credential or API key.

Severity

9.6 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

9.4 (Critical)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-82533"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-807"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-09-08T17:18:36Z",
    "severity": "CRITICAL"
  },
  "details": "DeepSeek Harness before 0.1.2-alpha.1 contains an authentication bypass vulnerability in its local HTTP control-plane API that allows attackers to gain full agent control by supplying a spoofed Host header, as the server validates only the client-supplied Host header value rather than the actual TCP connection origin. Attackers can exploit this flaw to invoke privileged commands such as commands/execute with danger-full-access permissions, escalate session approval policies to unconfined execution, and retrieve all stored conversations without any credential or API key.",
  "id": "GHSA-8m2g-8cgm-3vcp",
  "modified": "2026-09-10T15:32:55Z",
  "published": "2026-09-08T18:32:01Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-82533"
    },
    {
      "type": "WEB",
      "url": "https://github.com/deepseek-ai/deepseek-harness/commit/3e24087bfaeabe40b58ba2f7b936895b8f93fe27"
    },
    {
      "type": "WEB",
      "url": "https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.1.2-alpha.1"
    },
    {
      "type": "WEB",
      "url": "https://www.ox.security/blog/cve-2026-82533-deepseek-harness-ai-agent-sandbox-escape"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/deepseek-harness-alpha-1-authentication-bypass-via-host-header-spoofing"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-82533 (GCVE-0-2026-82533)

Vulnerability from cvelistv5 – Published: 2026-09-08 16:59 – Updated: 2026-09-10 14:57 X_Open Source

Title

DeepSeek Harness < 0.1.2-alpha.1 Authentication Bypass via Host Header Spoofing

Summary

DeepSeek Harness before 0.1.2-alpha.1 contains an authentication bypass vulnerability that grants unauthenticated access to its local HTTP agent-control API by accepting a client-supplied loopback Host header in place of validating the actual TCP connection origin. On the default configuration, a confined tool-executed process can reach the loopback API without any port exposure and use it to escape its own OS sandbox, escalate to unconfined execution, and disable the approval prompt. When the port is externally reachable via tunnel, SSH forward, or reverse proxy, a remote attacker can exploit the same flaw to create sessions, execute arbitrary commands, and exfiltrate stored conversation transcripts without credentials.

Severity

9.4 (Critical)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

9.6 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

SSVC

Exploitation: none Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-09-08 17:20 UTC

CWE

CWE-807 - Reliance on Untrusted Inputs in a Security Decision

Assigner

VulnCheck mitre root

References

4 references

URL	Tags
https://www.ox.security/blog/cve-2026-82533-deeps…	technical-descriptionexploit
https://github.com/deepseek-ai/deepseek-harness/r…	release-notes
https://github.com/deepseek-ai/deepseek-harness/c…	patch
https://www.vulncheck.com/advisories/deepseek-har…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
DeepSeek	DeepSeek Harness	Affected: 0 , < 0.1.2-alpha.1 (custom)

Date Public

2026-08-25 00:00

Credits

Nir Zadok (Nirza) Moshe Siman Tov Bustan

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-82533",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-08T17:20:59.863077Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-08T17:21:11.199Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:github/deepseek-ai/deepseek-harness",
          "product": "DeepSeek Harness",
          "repo": "https://github.com/deepseek-ai/deepseek-harness",
          "vendor": "DeepSeek",
          "versions": [
            {
              "lessThan": "0.1.2-alpha.1",
              "status": "affected",
              "version": "0",
              "versionType": "custom"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Nir Zadok (Nirza)"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Moshe Siman Tov Bustan"
        }
      ],
      "datePublic": "2026-08-25T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "DeepSeek Harness before 0.1.2-alpha.1 contains an authentication bypass vulnerability that grants unauthenticated access to its local HTTP agent-control API by accepting a client-supplied loopback Host header in place of validating the actual TCP connection origin. On the default configuration, a confined tool-executed process can reach the loopback API without any port exposure and use it to escape its own OS sandbox, escalate to unconfined execution, and disable the approval prompt. When the port is externally reachable via tunnel, SSH forward, or reverse proxy, a remote attacker can exploit the same flaw to create sessions, execute arbitrary commands, and exfiltrate stored conversation transcripts without credentials."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 9.4,
            "baseSeverity": "CRITICAL",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "PASSIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.6,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-807",
              "description": "Reliance on Untrusted Inputs in a Security Decision",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-10T14:57:09.857Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "Researcher Blog",
          "tags": [
            "technical-description",
            "exploit"
          ],
          "url": "https://www.ox.security/blog/cve-2026-82533-deepseek-harness-ai-agent-sandbox-escape/"
        },
        {
          "name": "Release Notes",
          "tags": [
            "release-notes"
          ],
          "url": "https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.1.2-alpha.1"
        },
        {
          "name": "Patch Commit",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/deepseek-ai/deepseek-harness/commit/3e24087bfaeabe40b58ba2f7b936895b8f93fe27"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/deepseek-harness-alpha-1-authentication-bypass-via-host-header-spoofing"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "tags": [
        "x_open-source"
      ],
      "title": "DeepSeek Harness \u003c 0.1.2-alpha.1 Authentication Bypass via Host Header Spoofing",
      "x_generator": {
        "engine": "vulncheck"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-82533",
    "datePublished": "2026-09-08T16:59:47.860Z",
    "dateReserved": "2026-08-29T17:20:57.082Z",
    "dateUpdated": "2026-09-10T14:57:09.857Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.