Skip to main content

Langchain-Chatchat CVE-2026-75128

| EUVDEUVD-2026-104685 CRITICAL
Missing Authentication for Critical Function (CWE-306)
2026-10-20 VulnCheck GHSA-5rx2-xp53-9x5r
9.3
CVSS 4.0 · Vendor: VulnCheck
View

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain

  1. Access
    Identify reachable Langchain-Chatchat endpoint
  2. Delivery
    POST to /tools/call naming shell tool
  3. Exploit
    Server invokes shell tool unauthenticated
  4. Execution
    Execute arbitrary OS command as root
  5. Impact
    Full host compromise

Vulnerability Assessment

Weakness
CWE
OWASP Top 10:2025
A07:2025 - Authentication Failures
ASVS 5.0
V6 - Authentication Authentication required for critical functions
MITRE ATT&CK

1 technique across 1 tactic: Initial Access

The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up.

Exploitation Conditions

No special conditions - remote unauthenticated exploitation against default deployments of Langchain-Chatchat (through 0.3.1.3), because the /tools/call endpoint requires no authentication and the shell tool is always registered and callable by name. The only practical prerequisites are network reachability of the Chatchat API server and the affected version range; no user interaction, credentials, or non-default configuration is needed. Impact is amplified in the shipped Docker image, where the server runs as root, so commands execute with root privileges rather than a limited account.

Impact

This is a genuine high-priority issue, not an inflated CVSS score. The vendor-supplied CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H, score 9.3) aligns cleanly with the description: a network-reachable POST /tools/call endpoint invokes any registered tool without authentication (CWE-306), and the always-registered shell tool yields arbitrary OS command execution. All three impact dimensions (confidentiality, integrity, availability) are High, and the shipped Docker image runs as root, so successful exploitation means full host compromise rather than a constrained service account. Publicly available exploit code exists (per the Lasso Security reference tagged as exploit and the VulnCheck advisory), which materially raises near-term risk. The vulnerability is NOT in CISA KEV at time of analysis and no EPSS score was provided, so there is no evidence of confirmed active exploitation or a quantified exploitation probability - the elevated risk here is driven by low attack complexity, no authentication, and public POC availability rather than observed in-the-wild activity. The signals are consistent with no major conflicts; the main caveat is that KEV and EPSS data are simply absent from the input, so widespread-vs-targeted exploitation cannot be judged from the data provided.

Exploit ScenarioDerived

A remote attacker locates an internet-exposed or network-reachable Langchain-Chatchat instance (through 0.3.1.3) and sends a single unauthenticated POST request to /tools/call naming the always-registered shell tool with an OS command payload. The server executes the command as its runtime user - root in the shipped Docker image - giving the attacker immediate arbitrary command execution. Public exploit code exists, and the low attack complexity (AC:L, no user interaction, no authentication) makes this trivially repeatable.

Act Now Prioritize within 24-48h. Why: CRITICAL severity + public POC available.
No patch listed yet 0.5% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Oct 20, 2026

Unauthenticated remote command execution in Langchain-Chatchat through version 0.3.1.3 allows any network-reachable attacker to invoke the built-in shell tool through the POST /tools/call endpoint and run arbitrary OS commands as the Chatchat server user. Because the shipped Docker image runs the service as root, successful exploitation typically yields root-level command execution. Publicly available exploit code exists; there is no CISA KEV confirmation of active exploitation at time of analysis.

RemediationAI

No vendor-released patch with an exact fixed version is identified in the provided data; upgrade only to a release the vendor confirms as fixed beyond 0.3.1.3. Until then, remove or disable the always-registered shell tool in the tool registry, which stops the direct command-execution path but removes shell tool functionality for legitimate users. Block POST /tools/call at the reverse proxy or require strong authentication in front of the Chatchat API, accepting that existing tool clients must be updated. Run the Docker image as a non-root user and restrict filesystem permissions and egress, which reduces post-exploitation impact but may require permission fixes for mounted volumes. Consult https://www.vulncheck.com/advisories/langchain-chatchat-through-0.3.1.3-unauthenticated-rce-via-tools-call-endpoint for updates.

Affected VersionsENISA

Langchain-Chatchat 0 ≤0.3.1.3

Affected Packages

euvd langchain_chatchat no fix

Source: OSV (Open Source Vulnerabilities)

Affects your stack

Affects 1 package in euvd

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

Langchain-Chatchat is an LLM application framework whose API server exposes tool_routes.py, where POST /tools/call maps to a generic dispatcher that resolves a tool by name from the registered tool registry and executes it. The shell tool is always registered, and the endpoint lacks any authentication or authorization check, matching CWE-306 missing authentication for a critical function. The CPE cpe:2.3:a:chatchat-space:langchain-chatchat:*:*:*:*:*:*:*:* identifies the product broadly, while the advisory scopes affected releases through 0.3.1.3. Exposure is highest for internet-facing deployments and the project Docker image, where the server process runs as root.

Know when Docker gets its next vulnerability

  • Watch products and get an email when something new is published
  • Check this CVE against your own stack and servers
  • Exploit and PoC references, threat intelligence from 22 sources

No credit card · 7-day full trial

Severity by source

Vendor (VulnCheck) PRIMARY 9.3 CRITICAL
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
vuln.today AI 9.8 CRITICAL

Endpoint is network-facing and unauthenticated (AV:N/PR:N/UI:N) with trivial single-request exploitation (AC:L), yielding arbitrary command execution with full C/I/A impact.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (VulnCheck).

CVSS VectorVendor: VulnCheck

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vulnerable system: Confidentiality
High
Vulnerable system: Integrity
High
Vulnerable system: Availability
High
Subsequent system: Confidentiality
None
Subsequent system: Integrity
None
Subsequent system: Availability
None

DescriptionCVE.org

Langchain-Chatchat through 0.3.1.3 exposes a POST /tools/call API endpoint that invokes any registered tool by name without authentication, leaving the always-registered shell tool callable. Remote attackers can send a single request naming the shell tool to execute arbitrary OS commands as the server user (root in the shipped Docker image).

Technical POC Analysis

CWE-306, Missing Authentication for Critical Function.

Full technical POC analysis - root cause, step-by-step exploitation and patch breakdown - is part of the Pro and Business plans.

Executive ViewAI

Why It Matters

Langchain-Chatchat, the open-source retrieval-augmented chat platform commonly used to build internal LLM assistants, carries a critical remote command execution flaw (CVE-2026-75128) affecting all releases through version 0.3.1.3 that lets an outside party run arbitrary operating-system commands on the host, and because the vendor's shipped Docker image runs as root, that access amounts to full control of the container and everything it can reach. Leadership should care because these deployments typically hold the organization's confidential document stores, vector databases, and LLM provider API keys, so a single compromised instance can cascade into broad data exposure and credential compromise. No vendor patch exists, so exposure will persist until the service is contained, rebuilt, or replaced.

Business Impact: High
Compensating Controls

No vendor-released patch identified at time of analysis. Interim mitigations: block or disable the POST /tools/call endpoint at a reverse proxy, API gateway, or WAF; restrict network access to trusted administrator ranges and remove internet exposure; run the container as a non-root user with a read-only root filesystem and dropped Linux capabilities; apply egress filtering to block access to cloud metadata services and internal management networks; and rotate all credentials reachable from the container.

Threat Intelligence Overview

EPSS Score
0.5%
Top 57% exploitable
Prevalence
Medium
popular open-source RAG/LLM app, limited true production footprint
Exploit
POC
Public exploit code exists
Data Quality
6 sources
Confidence: High

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue
Severity CRITICAL
CISA KEV No
Public POC Yes
EPSS 0.5%
Patch available No
Active threat No
Deciding rule
CRITICAL severity + public POC available
What every action level means
Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.
Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.
This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.
This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.
Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision
Out-of-Cycle
Exploitation
Poc
System Exposure· derived
Open
Automatable
Yes
Human Impact
High
Technical Impact
Total

Priority Score

67
Low Medium High Critical
KEV: 0
EPSS: +1
CVSS: +46
PoC: +20
Weaponized: 0
Threat intel: 0
Gov advisory: 0

Attack Technique

Authentication bypass attacks exploit flaws in the verification mechanisms that control access to systems and applications.

More in Docker

View all
CVE-2024-55964 CRITICAL POC
9.8 Mar 26

An issue was discovered in Appsmith before 1.52. Rated critical severity (CVSS 9.8), this vulnerability is remotely expl

CVE-2019-5736 HIGH POC
8.6 Feb 11

runc through version 1.0-rc6 (used in Docker before 18.09.2) contains a container escape vulnerability that allows attac

CVE-2023-32077 HIGH POC
7.5 Aug 24

Netmaker makes networks with WireGuard. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no a

CVE-2026-39987 CRITICAL POC
9.3 Apr 08

Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/

CVE-2023-5815 HIGH POC
8.1 Nov 22

The News & Blog Designer Pack - WordPress Blog Plugin - (Blog Post Grid, Blog Post Slider, Blog Post Carousel, Blog Post

CVE-2026-66384 MEDIUM POC
5.3 Aug 12

Path traversal in JFrog Artifactory (CWE-22) enables an authenticated low-privilege user to write data outside the inten

CVE-2014-9357 CRITICAL
10.0 Dec 16

Docker 1.3.2 allows remote attackers to execute arbitrary code with root privileges via a crafted (1) image or (2) build

CVE-2026-52806 CRITICAL POC
9.9 Jun 23

Remote code execution in Gogs through 0.14.2 allows authenticated users (and unauthenticated attackers on default-config

CVE-2025-14707 HIGH POC
8.9 Dec 15

Unauthenticated remote command injection in SGWBOX N3 firmware 2.0.25 lets attackers execute arbitrary operating-system

CVE-2026-56274 HIGH POC
8.7 Jun 23

Remote code execution in Flowise before 3.1.2 allows any authenticated user (or API caller with chatflow view/update per

CVE-2026-34156 CRITICAL POC
9.9 Mar 30

Remote code execution in NocoBase Workflow Script Node (npm @nocobase/plugin-workflow-javascript) allows authenticated l

CVE-2019-15752 HIGH POC
7.8 Aug 28

Docker Desktop Community Edition before 2.1.0.1 allows local users to gain privileges by placing a Trojan horse docker-c

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy