CVE-2026-51883
NVD: The knowledge base creation and document upload interfaces in Langchain-Chatchat 0.3.0;0.3.1 is vulnerable to path traversal. NVD: 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.
9.1 Severity
CRITICAL EPSS
0.0035 (26) KEV
-
Source-published summary
NVD: The knowledge base creation and document upload interfaces in Langchain-Chatchat 0.3.0;0.3.1 is vulnerable to path traversal. NVD: 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.
Possible impact
Source describes path traversal review. Possible impact: An attacker may be able to reach files outside the intended application path.
Affected context
Affected product or version requires source confirmation.
Remediation / advisory
Remediation reference present; patch status requires confirmation in the linked advisory.
Why it matters
Source describes path traversal review. Possible impact: An attacker may be able to reach files outside the intended application path.; CVSS 9.1 (CRITICAL); EPSS percentile 26; not listed in KEV; Remediation reference present; patch status requires confirmation in the linked advisory; sources: NVD.
What to verify
Confirm affected product/version, vendor advisory, patch or mitigation, and exposure.
Exposure hint
exposure unknown
Impact tags
Urgency reasons
Source-derived note
Summary derived from NVD description; unsafe procedural detail is not shown.
Redaction metadata
- source summary used
- True
- fallback summary used
- False
- unsafe procedural detail present
- false
- raw source displayed
- false
- public summary redacted
- true
Remediation handoff
Public-safe static handoff for human/Codex remediation planning. Scan, patch, external execution, and auto remediation are disabled.
Safety note
This radar shows source-published defensive context only. Exploit procedures, exploit strings, scanner commands, and auto-remediation are not provided.