CVE-2026-32617: Mintplexlabs Anythingllm Security Vulnerability (CVSS 7.1)

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh <file> for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the `AgentFlows` component. The vulnerability arises from improper handling of user input in the `loadFlow` and `deleteFlow` methods in `server/utils/agentFlows/index.js`. Specifically, the combination of `path.join` and `normalizePath` allows attackers to bypass directory restrictions and access or delete arbitrary `.json` files on the server. This can lead to information disclosure, such as leaking sensitive configuration files containing API keys, or denial of service by deleting critical files like `package.json`. The issue is resolved in version 1.12.1.

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL commands on connected databases. The getTableSchemaSql() method in all three database connectors (MySQL, PostgreSQL, MSSQL) constructs SQL queries using direct string concatenation of the table_name parameter without sanitization or parameterization.

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. If AnythingLLM prior to version 1.10.0 is configured to use Qdrant as the vector database with an API key, this QdrantApiKey could be exposed in plain text to unauthenticated users via the `/api/setup-complete` endpoint. Leakage of QdrantApiKey allows an unauthenticated attacker full read/write access to the Qdrant vector database instance used by AnythingLLM. Since Qdrant often stores the core knowledge base for RAG in AnythingLLM, this can lead to complete compromise of the semantic search / retrieval functionality and indirect leakage of confidential uploaded documents. Version 1.10.0 patches the issue.

qui is a web interface for managing qBittorrent instances. Versions 1.14.1 and below use a permissive CORS policy that reflects arbitrary origins while also returning Access-Control-Allow-Credentials: true, effectively allowing any external webpage to make authenticated requests on behalf of a logged-in user. An attacker can exploit this by tricking a victim into loading a malicious webpage, which silently interacts with the application using the victim's session and potentially exfiltrating sensitive data such as API keys and account credentials, or even achieving full system compromise through the built-in External Programs manager. Exploitation requires that the victim access the application via a non-localhost hostname and load an attacker-controlled webpage, making highly targeted social-engineering attacks the most likely real-world scenario. This issue was not fixed at the time of publication.

mcp-memory-service is an open-source memory backend for multi-agent systems. Prior to version 10.25.1, when the HTTP server is enabled (MCP_HTTP_ENABLED=true), the application configures FastAPI's CORSMiddleware with allow_origins=['*'], allow_credentials=True, allow_methods=["*"], and allow_headers=["*"]. The wildcard Access-Control-Allow-Origin: * header permits any website to read API responses cross-origin. When combined with anonymous access (MCP_ALLOW_ANONYMOUS_ACCESS=true) - the simplest way to get the HTTP dashboard working without OAuth - no credentials are needed, so any malicious website can silently read, modify, and delete all stored memories. This issue has been patched in version 10.25.1.