# CVE-2025-0185: Pandas Query Injection in langgenius/dify

> Attackers can execute arbitrary code via unsanitized inputs in the Dify Vanna module's Pandas query function.

- **Severity:** High 8.8 (`CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Any signed-in user
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 20 Mar 2025
- **Updated:** 20 Mar 2025
- **Also known as:** GHSA-mf57-6hg5-mrvm

## What is CVE-2025-0185?

CVE-2025-0185 is a high-severity code injection vulnerability in langgenius/dify, published on 20 Mar 2025. Any signed-in user can exploit it over the network, with no action from the victim.

### Official description

A vulnerability in the Dify Tools' Vanna module of the langgenius/dify repository allows for a Pandas Query Injection in the latest version. The vulnerability occurs in the function `vn.get_training_plan_generic(df_information_schema)`, which does not properly sanitize user inputs before executing queries using the Pandas library. This can potentially lead to Remote Code Execution (RCE) if exploited.

Weakness: CWE-94 (Improper Control of Generation of Code)

## Which versions are affected by CVE-2025-0185?

It affects 1 product.


Products: Dify Dify.

## How do I fix CVE-2025-0185?

No fix has been published for CVE-2025-0185 yet. Limit exposure of the affected software until one is available.

## Is CVE-2025-0185 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-0185 exists.

## Other vulnerabilities in langgenius/dify

- [CVE-2026-41947](https://insights.sbomify.com/CVE-2026-41947/): Dify < 1.14.2 Authorization Bypass via Trace Configuration Endpoints (critical 9.3)
- [CVE-2026-41948](https://insights.sbomify.com/CVE-2026-41948/): Dify v1.14.1 Path Traversal via Plugin Daemon Internal API Access (critical 9.3)
- [CVE-2026-61461](https://insights.sbomify.com/CVE-2026-61461/): Dify < 1.16.0-rc1 SQL Injection via MyScale Vector Store search_by_full_text (high 8.7)
- [CVE-2025-67732](https://insights.sbomify.com/CVE-2025-67732/): Dify Vulnerable to Plaintext API Key Exposure via Model Provider Configuration Endpoint (high 8.4)
- [CVE-2026-41949](https://insights.sbomify.com/CVE-2026-41949/): Dify < 1.14.2 Authorization Bypass via File Preview Endpoint (high 8.2)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2025-0185 and fix it if it is affected.

What it is: CVE-2025-0185 is a high-severity code injection vulnerability in langgenius/dify, published on 20 Mar 2025. Any signed-in user can exploit it over the network, with no action from the victim.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-0185 exists.

Affected product: langgenius/dify. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2025-0185/ (Markdown: https://insights.sbomify.com/CVE-2025-0185/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2025-0185
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-0185
- OSV: https://osv.dev/vulnerability/CVE-2025-0185

---
From sbomify Insights: https://insights.sbomify.com/CVE-2025-0185/
Summaries are generated and may contain mistakes; the official description above is the record.