Skip to content

Bump vLLM to 0.8.5 in affected runner requirements to remediate mooncake RCE advisory#863

Draft
Copilot wants to merge 2 commits into
mainfrom
copilot/fix-vllm-mooncake-security-issue
Draft

Bump vLLM to 0.8.5 in affected runner requirements to remediate mooncake RCE advisory#863
Copilot wants to merge 2 commits into
mainfrom
copilot/fix-vllm-mooncake-security-issue

Conversation

Copy link
Copy Markdown
Contributor

Copilot AI commented May 7, 2026

This addresses the Dependabot alert for GHSA-hj4w-hm2g-p6w5 / CVE-2025-32444 where vLLM versions >=0.8.0 are vulnerable (mooncake integration RCE path). The fix updates the alerted manifest to the lowest patched version to minimize churn.

  • Dependency update (minimal scope)

    • Updated only the alerted manifest:
      • code_snippets/runners-examples/vllm-tool-calling-llama-3.1-8b_requirements.txt
    • Changed:
      vllm==0.8.0
      to:
      vllm==0.8.5
  • Reachability Assessment

    • Advisory-specific indicators were checked in-repo (mooncake, recv_pyobj, kv_transfer, ZeroMQ).
    • No matching usage/configuration was found.
    • Current risk in this repo appears non-reachable from documented/example code paths; this version bump primarily resolves scanner-detected vulnerable pinning.
    • Confidence: High (advisory names concrete affected integration/API path and no corresponding usage exists here).

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

  • collector-prod.1am6wm210aow.us-south.codeengine.appdomain.cloud
    • Triggering command: /opt/hostedtoolcache/node/24.14.1/x64/bin/node /opt/hostedtoolcache/node/24.14.1/x64/bin/node /home/REDACTED/work/docs/docs/node_modules/@ibm/telemetry-js/dist/REDACTED-process.js --log=/tmp/ibmtelemetry-20260507T215431825Z-275940.log --config=telemetry.yml (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

Original prompt

This section details the Dependabot vulnerability alert you should resolve

<alert_title>vLLM Vulnerable to Remote Code Execution via Mooncake Integration</alert_title>
<alert_description>## Impacted Deployments

Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.

Description

vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack.

This is a similar to GHSA - x3m8 - f7g5 - qhm7, the problem is in

https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179

Here recv_pyobj() Contains implicit pickle.loads(), which leads to potential RCE.</alert_description>

critical
GHSA-hj4w-hm2g-p6w5, CVE-2025-32444
vllm
pip
<vulnerable_versions>= 0.8.0</vulnerable_versions>
<patched_version>0.8.5</patched_version>
<manifest_path>code_snippets/runners-examples/vllm-tool-calling-llama-3.1-8b_requirements.txt</manifest_path>

https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5 https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7 https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179 https://nvd.nist.gov/vuln/detail/CVE-2025-32444 https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-42.yaml https://github.com/advisories/GHSA-hj4w-hm2g-p6w5

<task_instructions>Resolve this alert by updating the affected package to a non-vulnerable version. Prefer the lowest non-vulnerable version (see the patched_version field above) over the latest to minimize breaking changes. Include a Reachability Assessment section in the PR description. Review the alert_description field to understand which APIs, features, or configurations are affected, then search the codebase for usage of those specific items. If the vulnerable code path is reachable, explain how (which files, APIs, or call sites use the affected functionality) and note that the codebase is actively exposed to this vulnerability. If the vulnerable code path is not reachable, explain why (e.g. the affected API is never called, the vulnerable configuration is not used) and note that the update is primarily to satisfy vulnerability scanners rather than to address an active risk. If the advisory is too vague to determine reachability (e.g. 'improper input validation' with no specific API named), state that reachability could not be determined and explain why. Include a confidence level in the reachability assessment (e.g. high confidence if the advisory names a specific API and you confirmed it is or is not called, low confidence if the usage is indirect and hard to trace). If no patched version is available, check the alert_description field for a Workarounds section — the advisory may describe configuration changes or usage patterns that mitigate the vulnerability without a version update. If a workaround is available, apply it and leave a code comment referencing the advisory identifier explaining it is a temporary mitigation. If neither a patch nor a workaround is available, explain in the PR description why the alert cannot be resolved automatically so a human reviewer can take over. Inspect the repository to determine which package manager is used (e.g. lock files, config files, build scripts) and use that tooling to perform the update — do not edit lock files directly. If the version constraint in the manifest (e.g. package.json, Gemfile, pyproject.toml) caps the version below the fix, update the constraint first. For transitive dependencies, determine whether it is simpler to update the direct dependency that pulls in the vulnerable package or to update the transitive dependency directly, and choose the least disruptive approach. If upgrading to fix the vulnerability forces a major version bump or known breaking changes, review the changelog or release notes, then audit the codebase for usage of affected APIs and fix any breaking changes that are found. If the package manager fails to resolve dependencies (e.g. peer dependency conflicts, incompatible engine constraints), document the error in the PR description rather than attempting increasingly complex wor...

Copilot AI requested review from Copilot and removed request for Copilot May 7, 2026 21:52
Copilot AI requested review from Copilot and removed request for Copilot May 7, 2026 21:57
Copilot AI changed the title [WIP] Fix vLLM vulnerability to remote code execution via mooncake integration Bump vLLM to 0.8.5 in affected runner requirements to remediate mooncake RCE advisory May 7, 2026
Copilot AI requested a review from muldercw May 7, 2026 21:58
@muldercw muldercw removed their request for review May 7, 2026 22:01
@muldercw muldercw requested a review from Alfrick May 7, 2026 22:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants