vulnerability / NVI-00011696 / Revision 3
vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
GitHub lists this reviewed advisory for vllm. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.
This report has not inspected your inventory, configuration, deployed build, reachability or evidence. A catalog listing and a severity score do not establish exposure or compromise.
01 / Meaning
Why it matters
Published affected context helps an owner decide what evidence to gather. This report has not examined your application.
3.1 low
GitHub source severity; exploitability and local consequence require separate evidence.
As of · GitHub Advisory Database
3.1 LOW (3.1)
security-advisories@github.com severity; no combined Null risk score.
0.216%
FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.12137. Missing scores are unknown.
As of · FIRST EPSS
02 / Applicability
The affected context
Affected versions, configuration prerequisites and known exclusions are public. Confirm each one against the deployed service.
vllm
source listed< 0.30.0
## Affected - **Ecosystem / package:** pip / `vllm` - **Affected versions:** vLLM ≤ 0.25.1 (confirmed on 0.25.1, commit `752a3a504485`). The lower bound predates 0.25.1; maintainers can confirm how far back the tool-continuation re-submission has omitted the salt. ## Summary On the GPT-OSS "Harmony" path (`POST /v1/responses`), a request that uses a built-in or MCP tool runs as a multi-turn loop: after each tool call vLLM re-renders the full next-turn Harmony prompt and re-submits it to the engine. Turn 1 correctly carries `request.cache_salt`, but the tool-continuation re-submission rebuilds the engine input via `tokens_input(token_ids)` with **no** `cache_salt`. The continuation prefix is therefore cached in the global *unsalted* namespace even though the caller opted into salting. A second tenant who can guess the low-entropy post-tool history submits the reconstructed continuation (unsalted) and reads exact per-turn cached-token counts from the Responses usage — restoring the prompt-membership oracle that `cache_salt` is documented to prevent. Silently dropping a preserved salt *after* the
03 / Response
What to do next
- investigate
Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.
Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system. FIRST EPSS
A fixed release is not deployment evidence.
Check current vendor support and compatibility. After making a change, verify the deployed build and relevant runtime conditions. Keep the evidence, owner and time. An updated lockfile alone does not prove what is running.
04 / Limits
What this report cannot establish
- Customer inventory, deployment, reachability and exploitation have not been inspected.
- NVD lastModified does not establish freshness of every associated CPE record.
05 / Provenance
Sources you can inspect
Each assertion retains its source. Mirrored records may repeat one underlying publisher; additional links are not independent corroboration.
- GHSA-935w-9g4m-p28p ↗
GitHub Advisory Database · vendor advisory
Observed . GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.
- CVE-2026-105752 ↗
NIST National Vulnerability Database · official catalog
Observed . This product uses data from the NVD API but is not endorsed or certified by the NVD.
- CVE-2026-105752 ↗
FIRST EPSS · official catalog
Observed . FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.
Public revision history
Only published revisions appear here. Routine fetches do not create a material-change event.
- Revision 3 ·
Source facts changed; compare the preserved prior revision.
- Revision 2 ·
Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.
- Revision 1 ·
First indexed by Null; source disclosure date is shown separately.