CriticalVulnerabilityLLM-specific

CVE-2026-27966: Langflow CSV Agent code execution through prompt injection

Source: NVD(opens in a new tab)
Identifier: CVE-2026-27966
Published: February 25, 2026
Record updated: October 25, 2026

Affected: langflow <= 1.8.0rc2
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 35.2%

Summary

CVE-2026-27966 affects Langflow versions prior to 1.8.0. The CSV Agent node hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain's `python_repl_ast` Python REPL tool. An attacker can use prompt injection to execute arbitrary Python and OS commands on the server, resulting in full Remote Code Execution (RCE). The weakness is classified as CWE-94.

Mitigation

Version 1.8.0 fixes the issue.

Details

Scores and exploitation

CVSS score: 9.8(critical)
EPSS: 35.2%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-94
Attack pattern (CAPEC): CAPEC-242
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Packages: langflow@<= 1.8.0rc2

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity,
Availability,
Safety
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-27966

First tracked: February 25, 2026 at 11:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

langflowPyPIReaches an LLM package through dependencies

Summary

Mitigation

Affected packages in the Exposure Registry

Related items