How severe is GHSA-2pc9-4j83-qjmr?

GHSA-2pc9-4j83-qjmr has a CVSS score of 8.8/10, rated HIGH. Immediate patching is strongly recommended.

Which packages are affected by GHSA-2pc9-4j83-qjmr?

GHSA-2pc9-4j83-qjmr affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-2pc9-4j83-qjmr?

Update vllm to 0.14.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-2pc9-4j83-qjmr is resolved across your whole dependency graph.

How do I detect GHSA-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr?

O3 pinpoints whether GHSA-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr actively exploited in the wild?

No public exploit code has been indexed for GHSA-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr?

GHSA-2pc9-4j83-qjmr has an EPSS (Exploit Prediction Scoring System) score of 0.5%, placing it in the 41th 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-2pc9-4j83-qjmr?

GHSA-2pc9-4j83-qjmr is classified as Code Injection (CWE-94). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation. This is a high-impact weakness class that often enables remote code execution or data exposure.

When was GHSA-2pc9-4j83-qjmr published, and has it been updated?

GHSA-2pc9-4j83-qjmr was published on January 21, 2026 and was last updated on February 4, 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-2pc9-4j83-qjmr

HIGH

vLLM affected by RCE via auto_map dynamic module loading during model initialization

Also known asCVE-2026-22807

Published

Jan 21, 2026

Updated

Feb 4, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

EPSS Exploitation Probability

via FIRST.org ↗

0.5%probability of exploitation in next 30 days

Lower Risk41th percentile+0.51%

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 loads Hugging Face auto_map dynamic modules during model resolution without gating on trust_remote_code, allowing attacker-controlled Python code in a model repo/path to execute at server startup.

Impact

An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load.
This happens before any request handling and does not require API access.

Affected Versions

All versions where vllm/model_executor/models/registry.py resolves auto_map entries with try_get_class_from_dynamic_module without checking trust_remote_code (at least current main).

Details

During model resolution, vLLM unconditionally iterates auto_map entries from the model config and calls try_get_class_from_dynamic_module, which delegates to Transformers’ get_class_from_dynamic_module and executes the module code.

This occurs even when trust_remote_code is false, allowing a malicious model repo to embed code in a referenced module and have it executed during initialization.

Relevant code

vllm/model_executor/models/registry.py:856 — auto_map resolution
vllm/transformers_utils/dynamic_module.py:13 — delegates to get_class_from_dynamic_module, which executes code

Fixes

https://github.com/vllm-project/vllm/pull/32194

Credits

Reported by bugbunny.ai

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	≥ 0.10.1&&< 0.14.0	0.14.0

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 0.14.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr 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-2pc9-4j83-qjmr. 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 loads Hugging Face `auto_map` dynamic modules during model resolution **without gating on `trust_remote_code`**, allowing attacker-controlled Python code in a model repo/path to execute at server startup. --- # Impact An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve **arbitrary code execution** on the vLLM host during model load. This happens **before any request handling** and does **not require API access**. --- # Affected Versions All versions where `vllm/model_executor/models/registry.py` resolves `auto_map`

O3 Security · Impact-Aware SCA

Is GHSA-2pc9-4j83-qjmr in your dependencies?

O3 detects GHSA-2pc9-4j83-qjmr 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