Langflow has Remote Code Execution in CSV Agent

langflow (pip)

1. Summary The CSV Agent node in Langflow hardcodes allow_dangerous_code=True, which automatically exposes LangChain’s Python REPL tool (python_repl_ast). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). 2.

First seen: 27 Feb 2026
Last update: 27 Feb 2026, 15:47 UTC
Identifiers: CVE-2026-27966
Source: GitHub advisory
On the menu as: PyPI packages
LLM gateways

Check this repository for exposure to one security incident from pwned.coffee. Report first, change nothing until I say so.

## Langflow has Remote Code Execution in CSV Agent
Severity: critical. Patch status: no fix yet.
Affected: langflow (pip)
Ids: CVE-2026-27966

1. Summary The CSV Agent node in Langflow hardcodes allow_dangerous_code=True, which automatically exposes LangChain’s Python REPL tool (python_repl_ast). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). 2.

## Steps
1. This incident involves a provider (ai-gateways). Search config, CI and env templates (.env.example, wrangler.toml, vercel.json, terraform, workflow secrets) for credentials stored there. List each secret by name, where it is used, and how to rotate it. Never print secret values.
2. There is no fix yet. Until one ships: restrict network access to it.

## Report
A table: file, product or package, version in use, affected yes/no, exact fix. Then anything a human has to check outside the repo.

If you have the pwned.coffee MCP server (https://pwned.coffee/mcp), call lookup_cve("CVE-2026-27966") for the latest, and check_repo with this repo's lockfiles, Dockerfiles and workflows for a full receipt.
Sources: https://github.com/advisories/GHSA-3645-fxcv-hqr4 https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508 https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4 https://github.com/pypa/advisory-database/tree/main/vulns/langflow/PYSEC-2026-376.yaml https://nvd.nist.gov/vuln/detail/CVE-2026-27966
https://pwned.coffee/i/langflow-has-remote-code-execution-in-csv-agent-cve-2026-27966

Sources

Wrong fix version, or a source we missed? Send it back to chef@pwned.coffee with the source, and we'll correct it here.

Totalone very hot coffee