Summary
OpenClaw: QMD memory_get restricts reads to canonical or indexed memory paths
The QMD backend memory_get read path accepted arbitrary workspace Markdown paths that were inside the workspace but outside the canonical memory locations or indexed QMD result set.
Affected versions
- Affected:
< 2026.4.15 - Patched:
2026.4.15
Impact
When the QMD backend was enabled, a caller with access to memory_get could read arbitrary *.md files under the configured workspace root, even when those files were not canonical memory files and had not been returned by QMD search. Severity remains low because exploitation requires access to the memory tool surface and is limited to workspace Markdown files, but it bypassed the intended memory-path policy.
Input manipulates file paths to reach files outside the intended directory, such as configuration or credential files. Typical impact: unauthorized file read or write outside the intended directory.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
OpenClaw 2026.4.15 restricts QMD reads to canonical memory paths or previously indexed QMD workspace paths. Workspace containment alone is no longer sufficient.
Verified in v2026.4.15:
extensions/memory-core/src/memory/qmd-manager.tsrejects non-default workspace Markdown paths unless they match an indexed QMD workspace read path.extensions/memory-core/src/memory/qmd-manager.test.tscovers QMD session search-result reads and the read-path restriction behavior.
Fix commit included in v2026.4.15 and absent from v2026.4.14:
37d5971db36491d5050efd42c333cbe0b98ed292via PR #66026
Thanks to @zsxsoft, Keen Security Lab, and @qclawer for reporting this issue.
Frequently Asked Questions
- What is GHSA-F934-5RQF-XX47? GHSA-F934-5RQF-XX47 is a medium-severity path traversal vulnerability in openclaw (npm), affecting versions < 2026.4.15. It is fixed in 2026.4.15. Input manipulates file paths to reach files outside the intended directory, such as configuration or credential files.
- Which versions of openclaw are affected by GHSA-F934-5RQF-XX47? openclaw (npm) versions < 2026.4.15 is affected.
- Is there a fix for GHSA-F934-5RQF-XX47? Yes. GHSA-F934-5RQF-XX47 is fixed in 2026.4.15. Upgrade to this version or later.
- Is GHSA-F934-5RQF-XX47 exploitable, and should I be worried? Whether GHSA-F934-5RQF-XX47 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether GHSA-F934-5RQF-XX47 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix GHSA-F934-5RQF-XX47? Upgrade
openclawto 2026.4.15 or later.