CVE-2023-29374

CVSS v3 9.8 CRITICAL

9.8^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

I

n LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

References

Link	Resource
https://github.com/hwchase17/langchain/issues/1026	Issue Tracking
https://github.com/hwchase17/langchain/issues/814	Exploit Issue Tracking Patch
https://github.com/hwchase17/langchain/pull/1119	Patch
https://twitter.com/rharang/status/1641899743608463365/photo/1	Exploit
https://github.com/hwchase17/langchain/issues/1026	Issue Tracking
https://github.com/hwchase17/langchain/issues/814	Exploit Issue Tracking Patch
https://github.com/hwchase17/langchain/pull/1119	Patch
https://twitter.com/rharang/status/1641899743608463365/photo/1	Exploit

Configurations

Configuration 1 (hide)

cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

History

21 Nov 2024, 07:56

Type	Values Removed	Values Added
References	~~() https://github.com/hwchase17/langchain/issues/1026 - Issue Tracking~~	() https://github.com/hwchase17/langchain/issues/1026 - Issue Tracking
References	~~() https://github.com/hwchase17/langchain/issues/814 - Exploit, Issue Tracking, Patch~~	() https://github.com/hwchase17/langchain/issues/814 - Exploit, Issue Tracking, Patch
References	~~() https://github.com/hwchase17/langchain/pull/1119 - Patch~~	() https://github.com/hwchase17/langchain/pull/1119 - Patch
References	~~() https://twitter.com/rharang/status/1641899743608463365/photo/1 - Exploit~~	() https://twitter.com/rharang/status/1641899743608463365/photo/1 - Exploit

Information

Published : 2023-04-05 02:15

Updated : 2025-02-12 17:15

NVD link : CVE-2023-29374

Mitre link : CVE-2023-29374

CVE.ORG link : CVE-2023-29374

JSON object : View

Products Affected

langchain

CWE

CWE-74

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

{"id": "CVE-2023-29374", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Primary", "source": "[email protected]", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}, {"type": "Secondary", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}]}, "published": "2023-04-05T02:15:37.340", "references": [{"url": "https://github.com/hwchase17/langchain/issues/1026", "tags": ["Issue Tracking"], "source": "[email protected]"}, {"url": "https://github.com/hwchase17/langchain/issues/814", "tags": ["Exploit", "Issue Tracking", "Patch"], "source": "[email protected]"}, {"url": "https://github.com/hwchase17/langchain/pull/1119", "tags": ["Patch"], "source": "[email protected]"}, {"url": "https://twitter.com/rharang/status/1641899743608463365/photo/1", "tags": ["Exploit"], "source": "[email protected]"}, {"url": "https://github.com/hwchase17/langchain/issues/1026", "tags": ["Issue Tracking"], "source": "af854a3a-2127-422b-91ae-364da2661108"}, {"url": "https://github.com/hwchase17/langchain/issues/814", "tags": ["Exploit", "Issue Tracking", "Patch"], "source": "af854a3a-2127-422b-91ae-364da2661108"}, {"url": "https://github.com/hwchase17/langchain/pull/1119", "tags": ["Patch"], "source": "af854a3a-2127-422b-91ae-364da2661108"}, {"url": "https://twitter.com/rharang/status/1641899743608463365/photo/1", "tags": ["Exploit"], "source": "af854a3a-2127-422b-91ae-364da2661108"}], "vulnStatus": "Modified", "weaknesses": [{"type": "Primary", "source": "[email protected]", "description": [{"lang": "en", "value": "CWE-74"}]}, {"type": "Secondary", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "description": [{"lang": "en", "value": "CWE-74"}]}], "descriptions": [{"lang": "en", "value": "In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method."}], "lastModified": "2025-02-12T17:15:18.260", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "7C55CEFC-7C13-4D07-A223-1C5E9F7BBF25", "versionEndIncluding": "0.0.131"}], "operator": "OR"}]}], "sourceIdentifier": "[email protected]"}