---
id: CVE-2026-82533
title: >-
  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 a…
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 a…
severity: critical
cvss: 9.6
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H'
cwe:
  - CWE-807
vendor: DeepSeek
product: DeepSeek Harness
affected:
  - harness < 0.1.2-alpha.1
published: '2026-09-08'
updated: '2026-09-10'
sourceUpdated: '2026-09-10T15:17:47.593'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-82533'
references:
  - url: >-
      https://github.com/deepseek-ai/deepseek-harness/commit/3e24087bfaeabe40b58ba2f7b936895b8f93fe27
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.1.2-alpha.1
    label: disclosure@vulncheck.com
  - url: >-
      https://www.ox.security/blog/cve-2026-82533-deepseek-harness-ai-agent-sandbox-escape/
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/deepseek-harness-alpha-1-authentication-bypass-via-host-header-spoofing
    label: disclosure@vulncheck.com
tags:
  - nvd
  - cve.org
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: total
  timestamp: '2026-09-08T17:20:59.863077Z'
epss: 0.01204
epssPercentile: 0.66962
ingestedAt: '2026-09-08T19:08:49.601Z'
---

## Overview

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.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.