Explore 4 source-supported AI security cases for 13.32 · Client-Side Code Execution in Databricks DASF 3.0, with evidence, scope, and defensive analysis.
Risk category
A malicious MCP server response causes code to run on the client. Crafted responses may inject scripts, exploit a client-side interpreter, or trigger unsafe response-processing behavior. Information received from the server becomes executable authority when the client fails to keep response data separate from code.
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: A malicious server response reaches new Function and executes on the client, exactly sharing the response-data-to-code failure. The response uses the model SSE protocol, not MCP. No MCP implementation or model-generated payload is inferred.
Model-protocol events and a conditional account-to-backend execution path; the malicious event need not be model-generated.
Pillar Security demonstrated code execution during remote MCP OAuth authentication in OpenCode, an AI coding agent, on Windows and WSL. A server-selected HTTPS authorization URL reached an unsafe PowerShell browser-launch command before any model decision. OpenCode 1.18.33 fixes this path; the later CVE-2026-119025 record also covers the shared open dependency and a separately validated MCP Inspector integration.
Why it relates: A malicious MCP authorization response becomes code in the client’s browser-launch path.
OpenCode and Inspector retain separate integration and version scopes; the common dependency does not merge their graphs.
The Backslash Security Research Team demonstrated that a Model Context Protocol (MCP) tool can be used as a vector for an indirect prompt injection attack on Cursor, potentially leading to the execution of malicious shell commands. The Backslash Security Research Team created a proof-of-concept MCP server capable of scraping webpages. When a user asks Cursor to use the tool to scrape a site containing a malicious prompt, the prompt is injected into Cursor's context. The prompt instructs Cursor to execute a shell command to exfiltrate the victim's AI agent configuration files containing credentials. Cursor does prompt the user before executing the malicious command, potentially mitigating the attack.
Why it relates: The Backslash Security Research Team demonstrated that a Model Context Protocol (MCP) tool can be used as a vector for an indirect prompt injection attack on Cursor, potentially leading to the execution of malicious shell commands. The relevant category is Client-Side Code Execution: A malicious MCP server response causes code to run on the client. Tool output proposes a credential-exfiltrating shell command, but user execution confirmation remains a required boundary.
The Backslash Security Research Team demonstrated that a Model Context Protocol (MCP) tool can be used as a vector for an indirect prompt injection attack on Cursor, potentially leading to the execution of malicious shell commands. The Backslash Security Research Team created a proof-of-concept MCP server capable of scraping webpages. When a user asks Cursor to use the tool to scrape a site containing a malicious prompt, the prompt is injected into Cursor's context. The prompt instructs Cursor to execute a shell command to exfiltrate the victim's AI agent configuration files containing credentials. Cursor does prompt the user before executing the malicious command, potentially mitigating the attack.
Tenet Threat Labs showed that attacker-injected Sentry events (error-monitoring records from the Sentry observability platform) can hijack AI coding agents through the Sentry MCP server. A public Sentry DSN lets an attacker submit a crafted error, the MCP integration returns it as diagnostic context, and Claude Code, Cursor, or Codex may execute a suggested npm command with developer or CI privileges. The control lesson: telemetry is data, not authority; MCP outputs, agent clients, tool gates, sandboxes, and egress policy all need runtime enforcement.
Why it relates: Tenet Threat Labs found 2,388 organizations with exposed Sentry DSNs and observed more than 100 coding agents execute a controlled validation package in authorized testing. The relevant category is Client-Side Code Execution: A malicious MCP server response causes code to run on the client.
Tenet Threat Labs found 2,388 organizations with exposed Sentry DSNs and observed more than 100 coding agents execute a controlled validation package in authorized testing. The source-backed chain begins with a crafted Sentry error event, crosses the Sentry MCP telemetry boundary, steers an agent toward an npx command, probes only bounded exposure metadata on the developer or CI runtime, and sends responsible-disclosure identifiers to Tenet's advisory tracker. This flow does not represent Tenet's controlled package as malicious credential theft and does not claim that the tested organizations were breached.