RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In versions 0.24.0 and prior, a Server-Side Template Injection (SSTI) vulnerability exists in RAGFlow's Agent workflow Text Processing (StringTransform) and Message components. These components use Python's jinja2.Template (unsandboxed) to render user-supplied templates, allowing any authenticated user to execute arbitrary operating system commands on the server. At time of publication, there are no publicly available patches.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In version 0.23.1 and possibly earlier versions, the MinerU parser contains a "Zip Slip" vulnerability, allowing an attacker to overwrite arbitrary files on the server (leading to Remote Code Execution) via a malicious ZIP archive. The MinerUParser class retrieves and extracts ZIP files from an external source (mineruserverurl). The extraction logic in extractzipnoroot fails to sanitize filenames within the ZIP archive. Commit 64c75d558e4a17a4a48953b4c201526431d8338f contains a patch for the issue.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In versions prior to 0.22.0, the use of an insecure key generation algorithm in the API key and beta (assistant/agent share auth) token generation process allows these tokens to be mutually derivable. Specifically, both tokens are generated using the same URLSafeTimedSerializer with predictable inputs, enabling an unauthorized user who obtains the shared assistant/agent URL to derive the personal API key. This grants them full control over the assistant/agent owner's account. Version 0.22.0 fixes the issue.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In versions prior to 0.23.0, a low-privileged authenticated user (normal login account) can execute arbitrary system commands on the server host process via the frontend Canvas CodeExec component, completely bypassing sandbox isolation. This occurs because untrusted data (stdout) is parsed using eval() with no filtering or sandboxing. The intended design was to "automatically convert string results into Python objects," but this effectively executes attacker-controlled code. Additional endpoints lack access control or contain inverted permission logic, significantly expanding the attack surface and enabling chained exploitation. Version 0.23.0 contains a patch for the issue.

Stored Cross-site Scripting (XSS) vulnerability in api.apps.dialogapp.setdialog in RAGFlow 0.17.2 allows remote attackers to execute arbitrary JavaScript via crafted input to the assistant greeting field, which is stored unsanitised and rendered using a markdown component with rehype-raw.

RAGFlow through 0.18.1 allows account takeover because it is possible to conduct successful brute-force attacks against email verification codes to perform arbitrary account registration, login, and password reset. Codes are six digits and there is no rate limiting.

A Server-Side Request Forgery (SSRF) vulnerability exists in infiniflow/ragflow version 0.12.0. The vulnerability is present in the POST /v1/llm/addllm and POST /v1/conversation/tts endpoints. Attackers can specify an arbitrary URL as the apibase when adding an OPENAITTS model, and subsequently access the tts REST API endpoint to read contents from the specified URL. This can lead to unauthorized access to internal web resources.

In infiniflow/ragflow version v0.12.0, there is an improper authentication vulnerability that allows a user to view another user's invite list. This can lead to a privacy breach where users' personal or private information, such as email addresses or usernames in the invite list, could be exposed without their consent. This data leakage can facilitate further attacks, such as phishing or spam, and result in loss of trust and potential regulatory issues.

An XSS vulnerability in infiniflow/ragflow version 0.12.0 allows an attacker to upload a malicious PDF file to the knowledge base. When the file is viewed within Ragflow, the payload is executed in the context of the user's browser. This can lead to session hijacking, data exfiltration, or unauthorized actions performed on behalf of the victim, compromising sensitive user data and affecting the integrity of the entire application.

In infiniflow/ragflow versions 0.12.0, the webcrawl function in documentapp.py contains multiple vulnerabilities. The function does not filter URL parameters, allowing attackers to exploit Full Read SSRF by accessing internal network addresses and viewing their content through the generated PDF files. Additionally, the lack of restrictions on the file protocol enables Arbitrary File Read, allowing attackers to read server files. Furthermore, the use of an outdated Chromium headless version with --no-sandbox mode enabled makes the application susceptible to Remote Code Execution (RCE) via known Chromium v8 vulnerabilities. These issues are resolved in version 0.14.0.

A stored cross-site scripting (XSS) vulnerability exists in infiniflow/ragflow, affecting the latest commit on the main branch (cec2080). The vulnerability allows an attacker to upload HTML/XML files that can host arbitrary JavaScript payloads. These files are served with the 'application/xml' content type, which is automatically rendered by browsers. This can lead to the execution of arbitrary JavaScript in the context of the user's browser, potentially allowing attackers to steal cookies and gain unauthorized access to user files and resources. The vulnerability does not require authentication, making it accessible to anyone with network access to the instance.

A vulnerability in infiniflow/ragflow versions v0.12.0 allows for remote code execution. The RPC server in RagFlow uses a hard-coded AuthKey 'authkey=b'infiniflow-token4kevinhu'' which can be easily fetched by attackers to join the group communication without restrictions. Additionally, the server processes incoming data using pickle deserialization via pickle.loads() on connection.recv(), making it vulnerable to remote code execution. This issue is fixed in version 0.14.0.

A vulnerability in infiniflow/ragflow version RAGFlow-0.13.0 allows for partial account takeover via insecure data querying. The issue arises from the way tenant IDs are handled in the application. If a user has access to multiple tenants, they can manipulate their tenant access to query and access API tokens of other tenants. This vulnerability affects the following endpoints: /v1/system/tokenlist, /v1/system/newtoken, /v1/api/tokenlist, /v1/api/newtoken, and /v1/api/rm. An attacker can exploit this to access other tenants' API tokens, perform actions on behalf of other tenants, and access their data.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. Versions 0.15.1 and prior are vulnerable to SQL injection. The ExeSQL component extracts the SQL statement from the input and sends it directly to the database query. As of time of publication, no patched version is available.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. An authenticated user can exploit the Insecure Direct Object Reference (IDOR) vulnerability that may lead to unauthorized cross-tenant access (list tenant user accounts, add user account into other tenant). Unauthorized cross-tenant access: list user from other tenant (e.g., via GET /<tenantid>/user/list), add user account to other tenant (POST /<tenantid>/user). This issue has not yet been patched. Users are advised to reach out to the project maintainers to coordinate a fix.

RAGFlow 0.13.0 suffers from improper access control in document-hooks.ts, allowing unauthorized access to user documents.

The addllm function in llmapp.py in infiniflow/ragflow version 0.11.0 contains a remote code execution (RCE) vulnerability. The function uses user-supplied input req['llmfactory'] and req['llmname'] to dynamically instantiate classes from various model dictionaries. This approach allows an attacker to potentially execute arbitrary code due to the lack of comprehensive input validation or sanitization. An attacker could provide a malicious value for 'llmfactory' that, when used as an index to these model dictionaries, results in the execution of arbitrary code.