hanzoai/flow
2
0
Fork 0
mirror of https://github.com/hanzoai/flow.git synced 2026-10-17 01:29:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: CSV agent RCE (#11798)

Browse Source 
* arbitrary-code-execution-warniing

* remove-parenthetical

* cleanup

* add-security-note

* remove-parenthetical
This commit is contained in:
Mendon Kissling
2026-02-24 14:20:34 +00:00
committed by GitHub
parent b2a3162b60
commit f2eeca5228
2 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SECURITY.md
+10
View File
@@ -98,6 +98,16 @@ A privilege escalation vulnerability exists in Langflow containers where an auth
**CVE**: [CVE-2025-57760](https://github.com/langflow-ai/langflow/security/advisories/GHSA-4gv9-mp8m-592r)
**Fixed in**: Langflow >= 1.5.1
### Arbitrary Code Execution in LangChain CSV Agent
The **CSV Agent** component (LangChain bundle) uses the `langchain-experimental` CSV agent, which can execute Python code generated by the LLM at runtime, such as to analyze the CSV with `pandas`.
This code runs in-process on the server and can perform any action the process can.
For more information, see [LangChain bundle documentation](https://docs.langflow.org/bundles-langchain#csv-agent).
**CVE:** [CVE-2024-21513](https://nvd.nist.gov/vuln/detail/CVE-2024-21513) (langchain-experimental arbitrary code execution).
**Fixed in**: Langflow >= 1.8.0
### No API key required if running Langflow with `LANGFLOW_AUTO_LOGIN=true` and `LANGFLOW_SKIP_AUTH_AUTO_LOGIN=true`
In Langflow versions earlier than 1.5, if `LANGFLOW_AUTO_LOGIN=true`, then Langflow automatically logs users in as a superuser without requiring authentication. In this case, API requests don't require a Langflow API key.
docs/docs/Components/bundles-langchain.mdx
+7
View File
@@ -11,6 +11,12 @@ This page describes the components that are available in the **LangChain** bundl
## CSV Agent
:::warning Security
Setting `allow_dangerous_code` to `true` allows the agent to execute arbitrary, LLM-generated Python code at runtime on the Langflow server.
This code can do anything that Python can do, so use this option only with trusted data and in a secure environment.
For more information, see [CVE-2024-21513](https://nvd.nist.gov/vuln/detail/CVE-2024-21513).
:::
This component is based on the [**Agent** core component](/agents).
This component creates a CSV agent from a CSV file and LLM.
@@ -20,6 +26,7 @@ For more information, see the [LangChain CSV agent documentation](https://python
| Name | Type | Description |
|------|------|-------------|
| allow_dangerous_code | Input parameter. | Default: `false`. Set to `true` to allow the agent to execute arbitrary Python code. For more information, see the [CSV Agent security warning](#csv-agent).
| llm | LanguageModel | Input parameter. The language model to use for the agent. |
| path | File | Input parameter. The path to the CSV file. |
| agent_type | String | Input parameter. The type of agent to create. |