AI & LLM Vulnerabilities

FastGPT (an AI platform for building AI agents) versions 4.14.8.3 and below have a critical security flaw where the fastgpt-preview-image.yml workflow uses pull_request_target (a GitHub feature that runs code with access to repository secrets) but executes code from an external contributor's fork, allowing attackers to run arbitrary code (commands on systems they don't own), steal secrets, and potentially compromise the production container registry (the central storage system for packaged software).

SQLBot, an intelligent data query system that uses a large language model and RAG (retrieval-augmented generation, where an AI pulls in external documents to answer questions), has a critical SQL injection vulnerability (a bug where an attacker tricks the system into running unintended database commands) in versions before 1.7.0 that allows authenticated users to execute arbitrary code on the backend server. The vulnerability exists because Excel sheet names are directly inserted into database commands without proper sanitization (cleaning/validation), and attackers can exploit this by uploading specially crafted files to gain complete control of the system.

SQLBot, a data query system combining AI with RAG (retrieval-augmented generation, where an AI pulls in external documents to answer questions), has a critical vulnerability in versions 1.5.0 and below that chains three security gaps: missing permission checks on file uploads, unsanitized storage of user input, and inadequate protections when inserting data into the AI's instructions. An attacker can exploit this to trick the AI into running malicious database commands that give them control over the database server.

Langflow's file upload endpoint (POST /api/v2/files/) is vulnerable to arbitrary file write (a type of attack that lets attackers save files anywhere on a server) because it doesn't properly validate filenames from multipart requests. Attackers who are logged in can use directory traversal characters (like "../") in filenames to write files outside the intended directory, potentially achieving RCE (remote code execution, where attackers can run commands on the server).

Mesop contains a critical vulnerability in its testing module where a `/exec-py` route accepts Python code without any authentication checks and executes it directly on the server. This allows anyone who can send an HTTP request to the endpoint to run arbitrary commands on the machine hosting the application, a flaw known as unauthenticated remote code execution (RCE, where an attacker runs commands on a system they don't own).

Mesop has a path traversal vulnerability (a technique where an attacker uses sequences like `../` to escape intended directory boundaries) in its file-based session backend that allows attackers to read, write, or delete arbitrary files on the server by crafting malicious `state_token` values in messages sent to the `/ui` endpoint. This can crash the application or give attackers unauthorized access to system files.

Langflow has an unauthenticated remote code execution vulnerability in its public flow build endpoint. The endpoint is designed to be public but incorrectly accepts attacker-supplied flow data containing arbitrary Python code, which gets executed without sandboxing when the flow is built. An attacker only needs to know a public flow's ID and can exploit this to run any code on the server.

CVE-2025-15060 is a remote code execution vulnerability in claude-hovercraft that allows attackers to run arbitrary code without needing to log in. The flaw exists in the executeClaudeCode method, which fails to properly validate user input before using it in a system call (a request to run operating system commands), allowing attackers to inject malicious commands.

MLflow versions before v3.7.0 contain a command injection vulnerability (a flaw where attackers insert malicious commands into input that gets executed) in the sagemaker module. An attacker can exploit this by passing a malicious container image name through the `--container` parameter, which the software unsafely inserts into shell commands and runs, allowing arbitrary command execution on affected systems.

Cloud CLI (a user interface for AI coding tools like Claude Code and Gemini-CLI) had a vulnerability before version 1.24.0 where attackers who had login access could run unauthorized commands on a computer by manipulating text inputs in Git-related features. This happened because the software used string interpolation (directly inserting user text into commands) without properly checking if the input was safe, which is a type of OS command injection (CWE-78, where an attacker tricks the system into executing arbitrary commands).

The MCP Atlassian tool's `confluence_download_attachment` function has a critical vulnerability where it writes downloaded files to any path on the system without checking directory boundaries. An attacker who can upload a malicious attachment to Confluence and call this tool can write arbitrary content anywhere the server process has write permissions, enabling arbitrary code execution (the ability to run any commands on the system), such as by writing a malicious cron job (a scheduled task) to execute automatically.

The `blockUnsafeOperationsPlugin` in simple-git fails to block unsafe git protocol overrides when the configuration key is written in uppercase or mixed case (like `PROTOCOL.ALLOW` instead of `protocol.allow`), because the security check uses a case-sensitive regex while git itself treats config keys case-insensitively. An attacker who controls arguments passed to git operations can exploit this to enable the `ext::` protocol, which allows arbitrary OS command execution (RCE, remote code execution where an attacker runs commands on a system they don't control).

WeKnora, an AI database query tool, has a critical Remote Code Execution (RCE, where an attacker can run commands on a system they don't own) vulnerability caused by incomplete validation in its SQL injection protection system. The validation framework fails to check PostgreSQL array expressions and row expressions, allowing attackers to hide dangerous functions inside these expressions and bypass all seven security phases, leading to arbitrary code execution on the database server.

WeKnora has a broken access control vulnerability (BOLA, or broken object-level authorization, where an attacker can access resources they shouldn't by manipulating object IDs) in its tenant management system that allows any authenticated user to read, modify, or delete any tenant without permission checks. Since anyone can register an account, attackers can exploit this to take over or destroy other organizations' accounts and access their sensitive data like API keys.

NLTK (Natural Language Toolkit, a Python library for text processing) versions 3.9.2 and earlier have a serious vulnerability in the StanfordSegmenter module, which loads external Java files without checking if they are legitimate. An attacker can trick the system into running malicious code by providing a fake Java file, which executes when the module loads, potentially giving them full control over the system.

Trivy VSCode Extension version 1.8.12 (a tool that scans code for security weaknesses) was compromised with malicious code that could steal sensitive information by using local AI coding agents (AI tools running on a developer's computer). The malicious version has been removed from the marketplace where it was distributed.

Langflow, a tool for building AI-powered agents and workflows, had a vulnerability in versions before 1.8.0 where the CSV Agent node automatically enabled a dangerous Python execution feature. This allowed attackers to run arbitrary Python and operating system commands on the server through prompt injection (tricking the AI by hiding instructions in its input), resulting in RCE (remote code execution, where an attacker can run commands on a system they don't own).

n8n, a workflow automation tool, has a vulnerability where authenticated users with permission to create or modify workflows can exploit expression evaluation (the process of interpreting code within workflow parameters) to execute arbitrary system commands on the host server. This is a serious security flaw because it allows attackers to run unintended commands on the underlying system.