CVE-2026-54561
MediumCVSS 6.2Exploitation Probability (EPSS)
Low risk15th percentile - higher than 15% of all known CVEs
Summary
MCP Memory Keeper is an MCP server for persistent context management in AI coding assistants. Prior to 0.13.0, context_import in src/index.ts passes the caller-controlled filePath directly to fs.readFileSync without restricting the path to an export directory. An MCP client, including an LLM agent induced to call the tool, can use ../ traversal or an absolute path to target any file readable by the server process. A valid JSON file is parsed and imported into the caller's session, allowing its full contents to be retrieved through context_get or context_export, while JSON.parse errors for non-JSON files can return leading file bytes in a SyntaxError message. The two disclosure modes can expose other exported sessions, JSON credentials or service-account files, environment files, and portions of SSH keys or other local files. This issue is fixed in version 0.13.0.
Risk Assessment
An attacker or induced LLM agent can read arbitrary files accessible to the server process, including credentials, environment files, and portions of SSH keys. This can lead to data leakage and enable further attacks.
Recommendation
Update MCP Memory Keeper to version 0.13.0 or later. Restrict the server process privileges and control which MCP tools can be invoked by LLM agents.
Related vulnerabilities
- CVE-2026-117691Critical
A flaw was found in the SAML HTTP-Redirect binding implementation of Keycloak. The issue occurs because the server processes percent-encoded parameter names (like %53AMLResponse) while the signature verification logic only checks literal parameter names. An attacker can use this discrepancy to provide a crafted, unsigned SAML message that the server processes instead of a legitimately signed one, leading to full account takeover of federated users.
- CVE-2026-96677Critical
Cross-site Scripting (XSS) vulnerability in Apache Juneau. HTML document serialization does not HTML-encode variable substitutions in page chrome fields (header, nav, footer, etc.), so applications that place request-derived values there reflect them unencoded.
- CVE-2026-73117Critical
HTTP Response Splitting (CRLF injection in HTTP headers) vulnerability in Apache Juneau. The REST server passed response header values and redirect targets to the servlet container unchecked, so request-derived data could allow header injection or redirect to an arbitrary site.
- CVE-2026-73116Critical
Insufficiently Protected Credentials vulnerability in Apache Juneau. The RestClient followed HTTP redirects while keeping credential headers from the original request, so a server redirecting to a different host, port, or from HTTPS to HTTP could receive Authorization, Cookie, Proxy-Authorization and X-API-Key headers.
- CVE-2026-73101Critical
Generation of Error Message Containing Sensitive Information vulnerability in Apache Juneau. The REST server sends the internal exception class and message to clients in a "Thrown" response header on every error response and may include internal exception messages in the error body, even with stack-trace rendering disabled.
- CVE-2026-73100Critical
Insertion of Sensitive Information into Log File vulnerability in Apache Juneau. The default REST server call logger records request headers for requests ending in a server error without redaction, so Authorization, Cookie, Proxy-Authorization and X-API-Key headers are written in cleartext to the application log.
- CVE-2026-73099Critical
Cross-Site Request Forgery (CSRF) vulnerability in Apache Juneau. The REST server accepts a "content" query parameter that replaces the request body and is enabled by default on every HTTP method including GET, so a cross-site link can deliver an attacker-chosen request body without a CORS preflight.
- CVE-2026-73098Critical
Improper control of dynamically-loaded code vulnerability in Apache Juneau. When parsing a value into a property of type java.lang.Class, the default class swap loaded the named class with initialization enabled, so input naming a class on the application classpath ran that class's static initializer.
- CVE-2026-121489Critical
Path Traversal vulnerability in Apache Juneau. The microservice DirectoryResource does not keep request paths inside its configured root directory; when an application enables the resource's view, upload or delete settings (all off by default), a client can read, write or delete files outside the root.
- CVE-2026-100109Critical
The Security For WooCommerce WordPress plugin from 1.0.10 to 1.0.16 does not perform capability checks when creating users through an action available to unauthenticated visitors, and lets the caller choose the new account's role. This allows unauthenticated attackers to create administrator accounts and take over the site.
Original NVD description (English source)
MCP Memory Keeper is an MCP server for persistent context management in AI coding assistants. Prior to 0.13.0, context_import in src/index.ts passes the caller-controlled filePath directly to fs.readFileSync without restricting the path to an export directory. An MCP client, including an LLM agent induced to call the tool, can use ../ traversal or an absolute path to target any file readable by the server process. A valid JSON file is parsed and imported into the caller's session, allowing its full contents to be retrieved through context_get or context_export, while JSON.parse errors for non-JSON files can return leading file bytes in a SyntaxError message. The two disclosure modes can expose other exported sessions, JSON credentials or service-account files, environment files, and portions of SSH keys or other local files. This issue is fixed in version 0.13.0.
Vulnerability data from NVD (NIST) · CISA KEV · EPSS

