# CVE-2026-49988: Repomix secret scanning bypass in MCP server tools

Source: https://junglewise.ai/threats/cve-2026-49988-repomix-secret-scanning-bypass-in-mcp-server-tools  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-07-15. Updated: 2026-07-15  
License: CC BY 4.0 with a link back

CVE-2026-49988 · Severity: medium · CVSS 4 · Published 2026-07-15

Repomix is a tool that prepares code repositories for use with AI models. A security flaw in its Model Context Protocol (MCP) server allows AI assistants or other tool-callers to read sensitive local files (such as .json, .txt, or .md files) that should be protected. This bypasses the tool's built-in secret-scanning safeguards, potentially exposing credentials or private configuration data to the AI model or its users.

Technologies: [repomix (npm)](https://junglewise.ai/threats/technologies/repomix). Vendors: [npm](https://junglewise.ai/threats/vendors/npm).

## Quick answers

**Is CVE-2026-49988 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-49988 being exploited in the wild.

**How severe is CVE-2026-49988?** Medium severity, with a CVSS score of 4, published 15 July 2026.

**Which products and versions are affected?** repomix (npm) <= 1.14.0, SEMVER:introduced=0,fixed=1.14.1.

**Is there a fix for CVE-2026-49988?** Yes. repomix (npm): upgrade to 1.14.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-49988 attacked?** It is attacked with local access, in a software library.

**Am I affected by CVE-2026-49988?** Check whether you run repomix (npm) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- repomix (npm): upgrade to 1.14.1 or later

  ```sh
  npm install repomix@1.14.1
  ```


## Technical details

A vulnerability exists in the Repomix MCP server where the 'attach_packed_output' and 'read_repomix_output' tools fail to enforce the 'runSecretLint()' safety check used by other file-reading tools. An attacker with the ability to invoke MCP tools can register an arbitrary local file (with .json, .txt, .md, or .xml extensions) as a 'packed output' without validation of the file's schema or content. Because the server does not verify if the file is a legitimate Repomix output and skips secret scanning during this specific workflow, sensitive information like API keys or configuration files can be exfiltrated. The fix in version 1.14.1 implements serve-time secret scanning for all attach-sourced outputs.

## Affected products

- yamadashy repomix < 1.14.1

## Identifiers

- CVE-2026-49988
- GHSA-hwpp-h97w-2h3j

## Timeline

- 2026-05-26: patched: Fix committed to repository
- 2026-05-27: advisory: GitHub Security Advisory published
- 2026-07-15: disclosed: CVE published to NVD

## References

- [https://github.com/yamadashy/repomix/commit/e447f7dba6f51fdb26bcad0c280542fca291960e](https://github.com/yamadashy/repomix/commit/e447f7dba6f51fdb26bcad0c280542fca291960e)
- [https://github.com/yamadashy/repomix/releases/tag/v1.14.1](https://github.com/yamadashy/repomix/releases/tag/v1.14.1)
- [https://github.com/yamadashy/repomix/security/advisories/GHSA-hwpp-h97w-2h3j](https://github.com/yamadashy/repomix/security/advisories/GHSA-hwpp-h97w-2h3j)

## Related threats

- [yamadashy Repomix argument injection in execGitShallowClone](https://junglewise.ai/threats/cve-2026-49987-yamadashy-repomix-argument-injection-in-execgitshallowclone)