Is this vulnerability remotely exploitable?

It can be, if the Agentic Assistant is exposed through a web UI or API where remote users or integrated systems can influence the prompts or other inputs that drive the LLM's output. In such cases, an attacker may be able to trigger code execution without direct system-level access, purely through crafted interactions with the Assistant.

What level of access does an attacker need to exploit this?

The attacker needs the ability to interact with the Agentic Assistant feature in a way that meaningfully steers the LLM's responses—for example, submitting prompts, providing contextual data, or controlling upstream sources the model consumes. Direct shell or file-system access is not required if the Assistant is reachable over the network.

What is the safest general fix pattern for developers?

The safest pattern is to prevent LLM-generated content from being executed as code at all. Instead, restrict AI output to declarative specifications (e.g., configuration objects, flow descriptions) and map those specifications onto pre-defined, vetted implementation components. Where code generation is necessary, keep it as an offline development aid with human review, not an automatic runtime execution path.

Severity:

CRITICAL RISK

(9.9)

Code Injection via LLM-Generated Python Execution (CWE-94) in Langflow Agentic Assistant

CVE-2026-33873

Published:

Mar 27, 2026

Status:

Analyzed

Summary

Affected Context

Exploit Preconditions

Why This Happens

Potential Impact

General Mitigation Guidance

How Teams Detect Issues Like This

Frequently Asked Questions

Source

NDV

Recent Vulnerabilities

CWE-77;CWE-78

HIGH RISK

HIGH

(7.3)

OS Command Injection (CWE-78) in Totolink A7100RU setGameSpeedCfg CGI Handler

Remote Code Execution on the Router

April 6, 2026

CWE-77;CWE-78

HIGH RISK

HIGH

(7.3)

OS Command Injection (CWE-78) in Totolink A7100RU setFirewallType Handler

Remote Code Execution on Router Firmware

April 6, 2026

Vulnerability Type

Category:

Code Injection

CWE:

CWE-94

Impact:

Remote Code Execution on the Langflow Server

Severity:

CRITICAL RISK

(9.9)

CVSS Version:

3.1

Vulnerability Type

Category:

Code Injection

CWE:

CWE-94

Impact:

Remote Code Execution on the Langflow Server

Severity:

CRITICAL RISK

(9.9)

CVSS Version:

3.1

Catch This CVE While Code Is Being Written

Detect vulnerable code directly in pull requests, so CVEs are fixed before merge.

Get Started

Ship clean & secure code faster

START 14 DAYS FREE TRIAL

BOOK A DEMO

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Code Injection via LLM-Generated Python Execution (CWE-94) in Langflow Agentic Assistant

Summary

Affected Context

Exploit Preconditions

Why This Happens

Potential Impact

General Mitigation Guidance

How Teams Detect Issues Like This

Frequently Asked Questions

Source

Recent Vulnerabilities

HIGH RISK

HIGH

(7.3)

OS Command Injection (CWE-78) in Totolink A7100RU setGameSpeedCfg CGI Handler

HIGH RISK

HIGH

(7.3)

OS Command Injection (CWE-78) in Totolink A7100RU setFirewallType Handler

Vulnerability Type

Vulnerability Type

Vulnerability Type

Catch This CVE While Code Is Being Written

Ship clean & secure code faster

Product

Pricing

Company

Legal

Developers

Compare

Product

Pricing

Company

Legal

Developers

Compare

Product

Pricing

Company

Legal

Developers

Compare