← Back to search

CVE-2026-51883

9.1 CRITICALpublic exploit available

Published 2026-10-01 · Updated 2026-10-05

AI risk analysis

Summary
The vulnerability allows an attacker to traverse directories and write content to arbitrary locations, potentially leading to unauthorized data access or modification.
Exploitability
Exploitation is relatively straightforward as it requires control over the `knowledge_base_name` parameter. The attacker must be able to inject path traversal sequences.
Blast radius
If exploited, this could lead to unauthorized access to sensitive files outside the intended directory, impacting data security and integrity.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to Langchain-Chatchat 0.3.2 or later.
path-traversaldata-leaksecurity

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

The knowledge base creation and document upload interfaces in Langchain-Chatchat 0.3.0;0.3.1 is vulnerable to path traversal. An attacker can inject path traversal sequences (such as `..\`) into the `knowledge_base_name` parameter to write knowledge base content to arbitrary locations outside the configured knowledge base root directory.

CVSS vector

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

Weaknesses

CWE-22

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.