Explore 3 source-supported AI security cases for 13.30 · Client-Side Data Leakage in Databricks DASF 3.0, with evidence, scope, and defensive analysis.
Risk category
Sensitive information leaks from client logs, caches, temporary files, or local storage. Credentials may be logged, responses may remain cached, or temporary material may survive without adequate cleanup. Data handled safely over the network can therefore still be exposed through the copies left on the client device.
Cato validated code execution and login-token theft through a malicious model endpoint in Open WebUI, a self-hosted AI-chat interface. The victim must use an enabled Direct Connections integration; the endpoint’s SSE execute event runs in the browser without requiring a model-generated attack. Reusing the token can additionally reach backend Python execution only when the account has workspace.tools permission.
Why it relates: The application’s localStorage token can be read and leaked by code executing in the browser origin. The storage surface is a model-chat client rather than an MCP client. The same client-local credential exposure mechanism is demonstrated.
Model-protocol events and a conditional account-to-backend execution path; the malicious event need not be model-generated.
Remus is Windows malware that steals application data after gaining execution on a device. SpyCloud identified AI-client directories among its configurable collection targets, including Codex, Cursor and OpenCode. The AI-security exposure is reusable credentials and locally retained activity data; protecting an agent tool alone does not contain malware already running elsewhere on the host.
Why it relates: Retained local AI-client artifacts are available to the host file collector. The shared client-copy leakage mechanism is supported; exact MCP cache implementations and policy violations are not established.
Host infostealer targeting AI-client credentials and retained files; no prompt injection or confirmed credential replay is asserted.
LayerX reported that Cursor (an AI coding IDE) stores API keys and session tokens in a local SQLite database that any installed Cursor extension can read. The attack does not need a prompt injection or user interaction after installation: a benign-looking extension can extract OpenAI, Anthropic, Google, or Cursor credentials and quietly exfiltrate them. The defensive lesson is that AI coding IDEs need protected credential storage, per-extension permission enforcement, and enterprise extension governance.
Why it relates: LayerX reported that Cursor (an AI coding IDE) stores API keys and session tokens in a local SQLite database that any installed Cursor extension can read. The relevant category is Client-Side Data Leakage: Sensitive information leaks from client logs, caches, temporary files, or local storage.
LayerX reported that Cursor (an AI coding IDE) stores API keys and session tokens in a local SQLite database that any installed Cursor extension can read. The attack does not need a prompt injection or user interaction after installation: a benign-looking extension can extract OpenAI, Anthropic, Google, or Cursor credentials and quietly exfiltrate them. The defensive lesson is that AI coding IDEs need protected credential storage, per-extension permission enforcement, and enterprise extension governance. The secret store was not a real boundary. LayerX says Cursor stores credentials in state.vscdb , not behind an OS keychain or credential manager. Any installed extension became a credential reader. A theme, helper, or productivity extension can query the local SQLite database without an obvious credential-access prompt. The blast radius leaves Cursor. The database can hold Cursor session tokens and OpenAI, Anthropic, or Google keys; stolen keys enable impersonation, paid API abuse, and prompt or completion exposure. This is extension supply chain, not model behavior. After installation, the attack path is local code reading local storage and sending the result to an attacker server. Trust semantics matter. If a product treats all extensions as the same local trust boundary, enterprises need extension allowlisting and protected storage before using real keys.