GHSA-rm76-4mrf-v9r8
LOWvLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
EPSS Exploitation Probability
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
vllmReal-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
Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.
Details
vLLM's prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions.
Impact
The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use.
Solution
We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.
Using a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.
To give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.
References
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | all versions | 0.7.2 |
Detection & mitigation playbook
Open-source dependencyDetect
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 0.7.2 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-rm76-4mrf-v9r8 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-rm76-4mrf-v9r8 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-rm76-4mrf-v9r8. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is GHSA-rm76-4mrf-v9r8 in your dependencies?
O3 detects GHSA-rm76-4mrf-v9r8 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.