Browse / MCP and Tool Server Flaws / Data exfiltration
Data exfiltration
10 records in MCP and Tool Server Flaws.
- FastMCP MCP client wrappers construct M2M OAuth providers without issuer binding — client secret redirectable to attacker-advertised authorization server An untrusted MCP server can advertise a different authorization server, so the client sends its OAuth client secret or signed assertion to the attacker.
- MCP TypeScript client SDK: HTTP client transports and OAuth requests followed cross-origin redirects and re-sent custom headers and request bodies Cross-origin redirects cause the client to resend custom headers and request bodies, including OAuth secrets, to an attacker-chosen origin.
- MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server A malicious MCP server can choose its own authorization server, so the client automatically sends stored refresh tokens and client secrets to it.
- MCP Atlassian: Path Traversal / Arbitrary File Read in confluence_upload_attachment MCP tool (incomplete fix of GHSA-xjgw-4wvw-rgm4) An MCP upload tool opens any local file path a caller supplies and posts its contents to an attacker-chosen Confluence host, since the earlier fix only covered downloads.
- MCP Atlassian: MCP HTTP Client Server-Local File Exfiltration via Unvalidated Attachment Upload Path An MCP attachment tool accepts any server-side file path, and attacker-supplied service headers redirect the upload so local files are sent to an attacker endpoint.
- Open WebUI: A user's session cookies are sent to tool servers configured for bearer authentication A tool call to a bearer-authenticated server can carry the user's session cookies because a shared callable reads a cookie jar built for a different connection.
- MCP Ruby SDK: Streamable HTTP transport lacks DNS-rebinding (Host/Origin) protection A webpage rebinds its hostname to localhost so the browser can call an unprotected local MCP Streamable HTTP server and read the results of its tools.
- n8n: "Allowed HTTP Request Domains" Restriction Bypass via AI Agents MCP Connector The agent's MCP tool path ignores the allowed-domain restriction on shared credentials, so a member can send a secret to an attacker-chosen URL.
- mcp-server-kubernetes argument injection can expose Kubernetes cluster credentials Leading-dash arguments evade the dangerous-flag check in kubectl tools, letting an attacker redirect kubectl to their server and receive the bearer token.
- Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled Domains The WebFetch trusted-domain check used prefix matching, so attacker domains that begin with a trusted name were fetched automatically, enabling data leakage.