CVE-2026-116096ggml-org llama.cpp Out-of-bounds Write
NVD
Vulnerability Summary
A weakness has been identified in ggml-org llama.cpp. Affected by this issue is the function list_pockettts_state_slots of the file tools/mtmd/models/pockettts-gen.cpp of the component Pocket-TTS. This manipulation of the argument mmproj causes out-of-bounds write. The attack requires local access. The exploit has been made available to the public and could be used for attacks. Upgrading to version b11796 can resolve this issue. Patch name: 0a1ef309cdbb9f2024f58a38fb4c42352c5db569. The affected component should be upgraded. The reported heap out‑of‑bounds write (gen‑audio / pocket‑tts state_out path) is no longer a silent exploitable heap write on current master and the latest release b11871 - a malicious mmproj that previously triggered it now trips a release‑active GGML_ASSERT and aborts. But the submitter's recommended by‑construction fix (PR #29360 "prevent OOB accesses from malformed mmproj files") is still open. So the root cause is detected‑and‑aborted, not prevented‑by‑design.
CVSS v4.0 Base Metrics — Score 4.8 (MEDIUM)
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:PAttack VectorLocal
Attack ComplexityLow
Attack RequirementsNone
Privileges RequiredLow
User InteractionNone
Confidentiality (Vulnerable System)Low
Integrity (Vulnerable System)Low
Availability (Vulnerable System)Low
Confidentiality (Subsequent System)None
Integrity (Subsequent System)None
Availability (Subsequent System)None
Show CVSS v3.x metrics (score 5.3)
CVSS v3.1 Base Metrics — Score 5.3 (MEDIUM)
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:CAttack VectorLocal
Attack ComplexityLow
Privileges RequiredLow
User InteractionNone
ScopeUnchanged
ConfidentialityLow
IntegrityLow
AvailabilityLow
Affected & Patched Versions
- ggml-org llama.cpp 0.4.0
- ggml-org llama.cpp 0.17.1
- ggml-org llama.cpp 55abc39
- ggml-org llama.cpp 55d4206c8
- ggml-org llama.cpp b5693
- ggml-org llama.cpp b7445
- ggml-org llama.cpp b7824
- ggml-org llama.cpp b8492
- ggml-org llama.cpp b8585
- ggml-org llama.cpp b9058
- ggml-org llama.cpp b9060
No patched version published yet
Until a fix ships, reduce exposure:
- Restrict access to the affected service or interface to trusted networks.
- Disable the affected feature if you do not need it.
- Watch the vendor advisory for a firmware or software update.
What to do
Prioritize this fix. Exploit code is public, so attacks can follow quickly.
- Check whether you run ggml-org llama.cpp and which version.
- No patched version is listed yet. Limit access to the affected service to trusted networks, and disable the feature if you can.
- Subscribe to the vendor advisory so you learn when a fix ships.
- Review logs and exposed services for signs of earlier compromise.
Timeline
- Oct 25, 2026Published
- Oct 26, 2026Record last modified
Score, severity and exploitation changes are tracked from the day Watchtower started logging them.
Get notified about new ggml-org llama.cpp CVEsYou are reading CVE-2026-116096. Get an email when KEV listings, exploits or new CVEs match your stack.
Set up CVE alertsMore ggml-org llama.cpp CVEs
External References
- Advisoryhttps://vuldb.com/vuln/426164
- Advisoryhttps://vuldb.com/vuln/426164/cti
- Advisoryhttps://vuldb.com/cve/CVE-2026-116096
- Advisoryhttps://vuldb.com/submit/1000891
- Exploithttps://github.com/3em0/cve_repo/tree/main/2026/llama.cpp.pockettts_state_heap_oob_rce
- Patchhttps://github.com/ggml-org/llama.cpp/pull/30902
- Exploithttps://github.com/3em0/cve_repo/tree/main/2026/llama.cpp.pockettts_state_heap_oob_rce/poc
- Patchhttps://github.com/ggml-org/llama.cpp/commit/0a1ef309cdbb9f2024f58a38fb4c42352c5db569
- Patchhttps://github.com/ggml-org/llama.cpp/releases/tag/b11796
- Referencehttps://github.com/ggml-org/llama.cpp/
Data last checked: Nov 16, 2026 14:12 UTC