Please find POC file here : https://trendmicro-my.sharepoint.com/:u:/p/kholoud_altookhy/IQCU4npQN4KOSoiORzvRN7DYAdXcmfcGG2ucFutTaV6uJ3M?e=Zdzx2t
ZDI-CAN-30459: Flowise CSV Agent Prompt Injection Remote Code Execution Vulnerability

-- CVSS -----------------------------------------

9.8: AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

-- ABSTRACT -------------------------------------

Trend Micro's Zero Day Initiative has identified a vulnerability affecting the following products:
Flowise - Flowise

-- VULNERABILITY DETAILS ------------------------

• Version tested: 3.1.1
• Installer file: https://github.com/FlowiseAI/Flowise (npm install flowise@3.1.1)
• Platform tested: Ubuntu 25.10

A prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed pyodide environment. An attacker can leverage this to execute arbitrary code in the context of the user running the server.

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Flowise. Authentication is not required to exploit this vulnerability.

The specific flaw exists within the run method of the CSV_Agents class. The issue results from insufficient input sanitization when using untrusted data to construct an LLM prompt. An attacker can leverage this vulnerability to execute code in the context of the service account.

Analysis

When a user makes a query against a chatflow using the CSV Agent node, the run method of the CSV_Agents class is called. This method reads the CSV file, loads a pyodide environment, and uses pandas to extract column names and data types into a dictionary. It then constructs a system prompt using that dictionary and the user's input, and sends this prompt to a configured LLM. The LLM response is stored in a variable named pythonCode. The method then attempts to validate this value using validatePythonCodeForDataFrame from packages/components/src/pythonCodeValidator.ts before evaluating it in pyodide.

The validator relies on a static regex blocklist. It can be bypassed using obfuscation techniques including string concatenation to reconstruct forbidden identifiers, chr() encoding, aliasing of dangerous builtins, __getattribute__ with concatenated attribute names, frame object inspection, MRO traversal, df.query() expression evaluation, and decorator syntax to invoke exec indirectly. Furthermore, pyodide is not sandboxed from the host operating system, so any Python code that passes the validator is executed with full access to OS interfaces.

From packages/components/nodes/agents/CSVAgent/CSVAgent.ts:

let pythonCode = ''
if (dataframeColDict) {
    const chain = new LLMChain({
        llm: model,
        prompt: PromptTemplate.fromTemplate(systemPrompt),
        verbose: process.env.DEBUG === 'true' ? true : false
    })
    const inputs = {
        dict: dataframeColDict,
        question: input // user-controlled input substituted into prompt
    }
    const res = await chain.call(inputs, [loggerHandler, ...callbacks])
    pythonCode = res?.text // LLM response assigned to pythonCode
    pythonCode = pythonCode.replace(/^```[a-z]+\n|\n```$/gm, '')
}

let finalResult = ''
if (pythonCode) {
    const validation = validatePythonCodeForDataFrame(pythonCode) // blocklist validation applied
    if (!validation.valid) {
        throw new Error(
            `Generated code was rejected for security reasons (${
                validation.reason ?? 'unsafe construct'
            }). Please rephrase your question to use only pandas DataFrame operations.`
        )
    }
    try {
        const code = `import pandas as pd\nimport numpy as np\n${pythonCode}`
        finalResult = await pyodide.runPythonAsync(code) // executed in unsandboxed pyodide
    } catch (error) {
        throw new Error(`Sorry, I'm unable to find answer for question: "${input}" using following code: "${pythonCode}"`)
    }
}

An unauthenticated attacker with the ability to send prompts to a chatflow using the CSV Agent node may use prompt injection to cause the LLM to respond with a malicious Python script. An authenticated attacker may instead configure a chatflow that points to an attacker-controlled server, which responds to LLM requests with an attacker-controlled Python payload, bypassing the LLM entirely.

Eight bypass variants were demonstrated against the validator:

Repro

The proof of concept (poc.py) has three modes of operation:

mode = "server": Starts a malicious server that responds to "/api/chat" requests with a JSON object containing an LLM response with the selected attack payload.

mode = "chatflow": Authenticates to the Flowise server, creates a chatflow with a CSV Agent node configured to use a ChatOllama model pointed at the malicious server, and triggers a prediction to execute the payload.

mode = "prompt_injection": Sends a prompt injection payload directly to an existing chatflow's prediction endpoint. Due to the nature of LLM responses, it may take multiple attempts or require a different injection technique depending on the model used.

python3 poc.py --mode [server OR chatflow OR prompt_injection] [--user <USER> --passwd <PASSWORD> --host <HOST> --r_host <R_HOST> --r_port <R_PORT> --l_port <L_PORT> --port <PORT> --cmd <CMD> --attack <ATTACK> --chatflow_id <CHAT_ID>]

-- CREDIT ---------------------------------------
This vulnerability was discovered by:
Dre Cura (@dre_cura) of TrendAI Research

-- FURTHER DETAILS ------------------------------

Supporting files:

If supporting files were contained with this report they are provided within a password protected ZIP file. The password is the ZDI candidate number in the form: ZDI-CAN-XXXX where XXXX is the ID number.

Please confirm receipt of this report. We expect all vendors to remediate ZDI vulnerabilities within 120 days of the reported date. If you are ready to release a patch at any point leading up to the deadline, please coordinate with us so that we may release our advisory detailing the issue. If the 120-day deadline is reached and no patch has been made available we will release a limited public advisory with our own mitigations, so that the public can protect themselves in the absence of a patch. Please keep us updated regarding the status of this issue and feel free to contact us at any time:

Zero Day Initiative
zdi-disclosures@trendmicro.com

The PGP key used for all ZDI vendor communications is available from:

http://www.zerodayinitiative.com/documents/disclosures-pgp-key.asc

-- INFORMATION ABOUT THE ZDI --------------------
Established by TippingPoint and acquired by Trend Micro, the Zero Day Initiative (ZDI) neither re-sells vulnerability details nor exploit code. Instead, upon notifying the affected product vendor, the ZDI provides its Trend Micro TippingPoint customers with zero day protection through its intrusion prevention technology. Explicit details regarding the specifics of the vulnerability are not exposed to any parties until an official vendor patch is publicly available.

Please contact us for further details or refer to:

http://www.zerodayinitiative.com

-- DISCLOSURE POLICY ----------------------------

Our vulnerability disclosure policy is available online at:

http://www.zerodayinitiative.com/advisories/disclosure_policy/