How severe is GHSA-3ww4-5jv9-j5gm?

GHSA-3ww4-5jv9-j5gm has a CVSS score of 6.5/10, rated MEDIUM. Review your exposure and patch according to your risk tolerance.

Which packages are affected by GHSA-3ww4-5jv9-j5gm?

GHSA-3ww4-5jv9-j5gm affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-3ww4-5jv9-j5gm?

Update vllm to 0.22.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-3ww4-5jv9-j5gm is resolved across your whole dependency graph.

How do I detect GHSA-3ww4-5jv9-j5gm in my PyPI dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

How do I mitigate GHSA-3ww4-5jv9-j5gm if there is no patch (or I can't update yet)?

If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

How does O3 Security protect against GHSA-3ww4-5jv9-j5gm?

O3 pinpoints whether GHSA-3ww4-5jv9-j5gm is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Is GHSA-3ww4-5jv9-j5gm actively exploited in the wild?

No public exploit code has been indexed for GHSA-3ww4-5jv9-j5gm yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for GHSA-3ww4-5jv9-j5gm?

GHSA-3ww4-5jv9-j5gm has an EPSS (Exploit Prediction Scoring System) score of 0.2%, placing it in the 11th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is GHSA-3ww4-5jv9-j5gm?

GHSA-3ww4-5jv9-j5gm is classified as CWE-345 (CWE-345). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was GHSA-3ww4-5jv9-j5gm published, and has it been updated?

GHSA-3ww4-5jv9-j5gm was published on June 10, 2026 and was last updated on July 17, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍 PyPI

GHSA-3ww4-5jv9-j5gm

MEDIUM

vLLM's Artifact Pin Decay allows pinned deployments to load unpinned code, weights, and processors

Also known asCVE-2026-47155PYSEC-2026-2301

Published

Jun 10, 2026

Updated

Jul 17, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

EPSS Exploitation Probability

via FIRST.org ↗

0.2%probability of exploitation in next 30 days

Lower Risk11th percentile+0.06%

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

1 pkg affected

🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Summary

vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision.

This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision.

Details

The expected invariant is:

When a vLLM operator supplies a model or code revision pin, every code, config, processor, weight file, side weight, and same-repository subfolder artifact loaded as part of that model should resolve under that pin unless vLLM exposes and enforces a separate explicit pin for that artifact.

Current main was verified affected at commit 3795d7acf431980e62e738493f437ae2a51549da.

Affected source boundaries:

vllm/model_executor/models/registry.py:1045-1051 and :1058-1064
- _try_resolve_transformers() passes revision=model_config.revision and trust_remote_code=model_config.trust_remote_code, but omits code_revision=model_config.code_revision for external auto_map dynamic module imports.
vllm/model_executor/model_loader/gguf_loader.py:58-60
- The direct-file GGUF form repo/file.gguf calls hf_hub_download(repo_id=repo_id, filename=filename) without passing revision.
vllm/model_executor/models/roberta.py:203-209
- BGE-M3 secondary sparse and ColBERT side weights are declared with revision=None.
vllm/model_executor/models/kimi_k25.py:111-114
- Kimi-K2.5 calls cached_get_image_processor() without passing model_config.revision.
vllm/model_executor/models/kimi_audio.py:92-95
- Kimi-Audio loads Whisper config from the whisper-large-v3 subfolder without a revision argument.
vllm/model_executor/models/kimi_audio.py:425-430
- Kimi-Audio declares same-repository whisper-large-v3 secondary weights with revision=None.
vllm/model_executor/model_loader/default_loader.py:287-301
- The default loader preserves model_config.revision for the primary source, then consumes model-supplied secondary sources as declared.

The strongest example is Kimi-Audio: the primary moonshotai/Kimi-Audio-7B-Instruct weights preserve the configured model revision, but the same-repository whisper-large-v3 audio tower config/weights do not. A pinned Kimi-Audio deployment can therefore load the Whisper subfolder outside the audited revision.

This report does not claim a trust_remote_code=False bypass, unauthenticated RCE, or real artifact compromise. The issue is improper propagation of explicit artifact pins across supported loader paths.

Impact

Affected users are operators who pin vLLM model deployments to a reviewed Hugging Face revision for safety review, provenance, rollback, or reproducibility. The impact is that the pin does not reliably describe the full set of artifacts vLLM serves. Even when the operator selects an audited revision, vLLM can resolve behavior-affecting secondary artifacts from the repository default branch or another mutable ref.

Depending on the model path, the unpinned artifact can be dynamic model code, a GGUF file, an image processor, retrieval side weights, or the same-repository Kimi-Audio Whisper subfolder weights/config.

This breaks the operational guarantee of a pinned deployment: "serve the exact artifact set I reviewed." A later change to an unpinned secondary artifact can alter model behavior without changing the operator's configured revision, making review, rollback, incident response, and audit records unreliable.

Occurrences

vllm/model_executor/models/kimi_k25.py L111-L114 — Kimi-K2.5 loads its image processor with cached_get_image_processor() but does not pass self.ctx.model_config.revision. The processor can therefore resolve from the default repository revision even when the model deployment is pinned.
vllm/model_executor/models/kimi_audio.py L425-L430 — Kimi-Audio declares same-repository whisper-large-v3 secondary weights with revision=None. A pinned Kimi-Audio deployment can therefore load the Whisper audio tower weights from an unpinned/default revision.
vllm/model_executor/models/kimi_audio.py L92-L95 — Kimi-Audio loads Whisper config from the same repository's whisper-large-v3 subfolder without passing the top-level model revision. The config for this behavior-affecting subcomponent can be resolved outside the audited model revision.
vllm/model_executor/models/registry.py L1058-L1064 — The later dynamic model-class resolution repeats the same pin-decay pattern: it forwards revision and trust_remote_code, but omits code_revision. This means an operator-provided code pin is not enforced at the dynamic module loader boundary.
vllm/model_executor/model_loader/gguf_loader.py L58-L60 — The direct GGUF form repo/file.gguf calls hf_hub_download(repo_id=repo_id, filename=filename) without passing model_config.revision. A deployment that pins the model revision can therefore resolve this GGUF file from the repository default revision.
vllm/model_executor/models/registry.py L1045-L1051 — try_get_class_from_dynamic_module() is called for external auto_map config/model classes with revision=model_config.revision, but without forwarding model_config.code_revision. When --code-revision is set, this dynamic module resolution can still fall back to the default code revision instead of the audited code revision.
vllm/model_executor/models/roberta.py L203-L209 — BgeM3EmbeddingModel creates same-repository secondary sparse/ColBERT weight sources with revision=None. The primary model revision is not propagated to these side weights, so they can be downloaded outside the operator-selected model revision.

Fixes

This was fixed in: https://github.com/vllm-project/vllm/pull/42616

Originally filed via huntr: https://huntr.com/bounties/3f1e24c0-87d2-4f6c-a705-820f380879ac.

The vLLM maintainer (Russell Bryant) redirected the report to the private GHSA channel. Offline proof bundle (vllm_artifact_pin_decay_bundle_verify.py + bundle-verification-20260430T143506Z.json) is available upon request.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	all versions	0.22.0

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.
Fix
Update vllm to 0.22.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-3ww4-5jv9-j5gm is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 pinpoints whether GHSA-3ww4-5jv9-j5gm is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-3ww4-5jv9-j5gm. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

### Summary vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies `--revision` or `--code-revision` can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. ### Details The expected invarian

O3 Security · Impact-Aware SCA

Is GHSA-3ww4-5jv9-j5gm in your dependencies?

O3 detects GHSA-3ww4-5jv9-j5gm across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

Scan my dependencies How O3 SCA works