CVE-2026-105752: vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
Noroxi assessment
Priority: Monitor (action score 12/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.21% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. Special conditions such as timing or configuration are required.
- Fixed version: vllm-project vllm 0.30.0.
Low priority for now. Upgrade to vllm-project vllm 0.30.0 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.
- Published
- Oct 5, 2026
- Updated
- Oct 8, 2026
- EPSS
- 0.2% · 12th percentile
- CWE
- CWE-200
Report tools
Action score
12
Monitor
Low priority for now.
- CVSS
- 12 / 40 · 3.1 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.2%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · GitHub_M
- 3.1
- NVD has not scored this yet; the score shown is the CNA’s.
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Running WordPress? Scan your site free with WP Lens
Noroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| vllm | vllm | cpe:2.3:a:vllm:vllm |
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- vllm vllmbefore 0.30.0
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
vllm-project vllm
- < 0.30.0affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | vllm | before 0.30.0 | 0.30.0 |
Same product
vllm: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-22778vLLM leaks a heap address when PIL throws an error60This week
- CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration40Plan
- CVE-2024-11041Remote Code Execution in vllm-project/vllm40Plan
Published before and after this one in the same product
- ← EarlierCVE-2026-100654Sep 26, 2026 · vLLM before 0.29.0 Denial of Service via out-of-range stop_token_ids28Monitor
- ← EarlierCVE-2026-103241Sep 30, 2026 · vllm-project vLLM Gemma4UnifiedParser gemma4.rs denial of service22Monitor
- Later →CVE-2026-105753Oct 5, 2026 · vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core26Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| vllm-project vllm | 0.30.0 · description | Vendor (CNA) |
| PyPI:vllm | 0.30.0 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
- Published
- Fix recordedsame day
- TodayNov 4, 2026+30 d
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
No credits in the CNA record.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-53923105 days apartvLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow21Monitor
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
—
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- Special conditions such as timing or configuration are required.
If successful
- Confidentiality
- none
- Integrity
- low · data or configuration can be modified
- Availability
- none
- Attack vector
- Network
- Attack complexity
- High
- Privileges required
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality impact
- None
- Integrity impact
- Low
- Availability impact
- None
Weakness class (CWE)
CWE-200 · Exposure of Sensitive Information to an Unauthorized ActorCVSS vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N
nvd-secondary
Root cause
The extension requests broader permissions than its function needs and sends the data it collects out for purposes beyond its stated function.
The bug in code
The whole CWE-200 classA representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.
Vulnerable
{
"permissions": ["tabs", "<all_urls>"],
"background": { "service_worker": "analytics.js" }
}Fixed
{
"permissions": ["activeTab"],
"host_permissions": ["https://yildiz.example/*"]
}Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- ExcavationCAPEC-116likelihood: High · Medium
- Subverting Environment Variable ValuesCAPEC-13likelihood: High · Very High
- FootprintingCAPEC-169likelihood: High · Very Low
- Exploiting Trust in ClientCAPEC-22likelihood: High · High
- FingerprintingCAPEC-224likelihood: High · Very Low
- ICMP Echo Request PingCAPEC-285likelihood: Medium · Low
- TCP SYN ScanCAPEC-287Low
- Enumerate Mail Exchange (MX) RecordsCAPEC-290Low
ATT&CK techniques
- System Service DiscoveryT1007
- System Network Configuration DiscoveryT1016
- Remote System DiscoveryT1018
- System Owner/User DiscoveryT1033
- Masquerading: Match Legitimate Name or LocationT1036.005
- Network Service ScanningT1046
- System Network Connections DiscoveryT1049
- Process DiscoveryT1057
- Permission Groups DiscoveryT1069
- System Information DiscoveryT1082
- File and Directory DiscoveryT1083
- Account DiscoveryT1087
- Multi-Factor Authentication InterceptionT1111
- Peripheral Device DiscoveryT1120
- System Time DiscoveryT1124
- Access Token Manipulation:Token Impersonation/TheftT1134.001
Change log
- SSVC exploitation— → none
- Exploit maturity— → none
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (4 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.