Skip to main content

CVE-2026-54561: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in mkreyman mcp-memory-keeper

0
Medium
VulnerabilityCVE-2026-54561cvecve-2026-54561cwe-22cwe-209
Published: 09/15/2026 (09/15/2026, 16:32:01 UTC)
Source: CVE Database V5
Vendor/Project: mkreyman
Product: mcp-memory-keeper

Description

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.

CVSS v3.1

Score 6.2medium

Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected software

mkreyman

mcp-memory-keeper

Affected versions
<0.13.0
GitHub Actionsmore threats →ai
mkreyman/mcp-memory-keeper
pkg:github/mkreyman/mcp-memory-keeper
Affected versions
<0.13.0

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/15/2026, 17:02:02 UTC

Technical Analysis

The vulnerability in mcp-memory-keeper (before 0.13.0) involves improper limitation of pathname to a restricted directory (CWE-22). The context_import function in src/index.ts uses fs.readFileSync on a caller-controlled filePath without path restriction, enabling directory traversal via '../' or absolute paths. This allows reading arbitrary files readable by the server process. Valid JSON files are parsed and imported into the caller's session, exposing their full contents through context_get or context_export. For non-JSON files, JSON.parse errors may leak leading file bytes in error messages (CWE-209). This can disclose sensitive data such as exported sessions, credentials, environment variables, and SSH key fragments. The vulnerability is fixed in version 0.13.0.

Potential Impact

An attacker or a malicious LLM agent can exploit this vulnerability to read arbitrary files on the server running mcp-memory-keeper, potentially exposing sensitive information including credentials, service account files, environment variables, and SSH keys. The vulnerability does not allow code execution or denial of service but results in confidentiality loss. The CVSS 3.1 base score is 6.2 (medium severity), reflecting local attack vector with low complexity and no privileges required.

Mitigation Recommendations

Upgrade mcp-memory-keeper to version 0.13.0 or later, where the vulnerability is fixed by restricting file path access in context_import. No other mitigations are indicated by the vendor advisory. Patch status is confirmed fixed in 0.13.0.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-06-15T19:04:14.457Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6aa9769455bf5e2cf5196303

Added to database: 09/15/2026, 16:47:16 UTC

Last enriched: 09/15/2026, 17:02:02 UTC

Last updated: 09/16/2026, 03:07:31 UTC

Views: 11

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses