Raw vector
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:XSummary
CVE-2026-33873 is a critical-severity Code Injection (CWE-94) vulnerability in Langflow Langflow. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 29% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-33873 is a critical code injection vulnerability (CWE-94) in Langflow, an open-source tool for building and deploying AI-powered agents and workflows. In versions prior to 1.9.0, the Agentic Assistant feature executes Python code generated by a large language model (LLM) during its validation phase. This process, intended to validate generated component code, instead dynamically executes the code server-side by reaching execution sinks and instantiating the generated class, enabling arbitrary Python code execution. The vulnerability carries a CVSS v3.1 base score of 9.9 (AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H).
An attacker requires low-privilege access (PR:L) to the Agentic Assistant feature over the network with no user interaction needed. By influencing the LLM's output—such as through crafted prompts or model manipulation—the attacker can inject malicious Python code that executes server-side. Successful exploitation grants full control over the affected Langflow instance, potentially leading to complete compromise with high confidentiality, integrity, and availability impacts due to the changed scope (S:C).
The patch in Langflow version 1.9.0 addresses the issue by fixing the validation logic in the Agentic Assistant, preventing dynamic execution of LLM-generated code. Detailed code changes are visible in the project's GitHub repository, including modifications to router.py (lines 252-297), schemas.py (lines 20-31), code_extraction.py (lines 11-53), validation.py (lines 27-47), and assistant_service.py (lines 142-156), which eliminate the execution sinks.
This vulnerability highlights risks in AI/ML workflows where LLM outputs directly feed into code execution paths, with no reported real-world exploitation as of publication on 2026-03-27.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-16815
Vulnerability Data
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,…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- AI-specific weaknesses CR
- CWE-1426 — LLM-generated code reaches execution sink with no validation.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: ai, langflow, llm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation finds code paths that accept and execute externally influenced strings.
Input validation directly stops untrusted data from being used to construct executable code without neutralization.
Least privilege limits the damage an injected code fragment can perform once executed.
Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).
PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.