GHSA-6c4r-fmh3-7rh8
MEDIUMvLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
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
Issue Description
Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in:
- Inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer).
Attack Scenario and Impact
LFE (Low-Frequency Effects) Channel Exploit
Attackers can craft special multichannel audio files containing:
- Normal content in front channels (L/R)
- Either interference signals or hidden content in the LFE channel
Notice: It is worth noting that not only the LFE channel is excluded, but in fact, channels beyond the 6th (such as rear surround channels, overhead channels, height speakers, etc.) are also not supported.
Attack Methodology:
Attackers can create specially engineered multichannel audio with LFE interference, where front channels (L/R) contain normal content while the LFE channel carries interference signals or hidden content. When played on consumer devices that ignore LFE channels, only the normal content is heard. However, when processed by AI systems using Librosa (which mixes all channels), the LFE interference affects speech recognition feature extraction or masks critical detection features. This enables malicious content to bypass AI detection while still reaching end users, potentially compromising voice authentication systems, evading content moderation, or disrupting speech recognition accuracy.
Potential Exploitation Scenarios:
- Voice authentication systems may be tricked into accepting anomalous audio
- Content moderation systems may fail to detect prohibited content hidden in LFE channels
- Speech recognition systems may produce incorrect transcriptions
Note: torch.audio implements this correctly. Failure to do so may lead to inconsistencies between training and test audio, resulting in performance degradation.
Resources
Fixes
- https://github.com/vllm-project/vllm/pull/37058, which removes the librosa dependency from vLLM.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.5.5&&< 0.18.0 | 0.18.0 |
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 0.18.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-6c4r-fmh3-7rh8 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-6c4r-fmh3-7rh8 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-6c4r-fmh3-7rh8. 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-6c4r-fmh3-7rh8 in your dependencies?
O3 detects GHSA-6c4r-fmh3-7rh8 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.