Skip to main content
VulnerabilityPublished

CVE-2026-107183: ggml-org llama.cpp · Use After Free

Affects ggml-org llama.cppSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 9.2 Critical : upgrade to b11393 as a priority.

Data as of 20 Nov 2026, 17:34 UTC

CVSS 4.0 base score
9.2Critical
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.4% chance of exploitation in 30 days – higher than 36% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in b11393
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 7 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 20 Nov 2026.

What to do

Upgrade ggml-org llama.cpp to b11393.

Affected software

ProductAffectedFixed in
ggml-orgllama.cppAffected
  • =b8227
Fixed in
  • b11393
GitHubggml-org/llama.cpppkg:github/ggml-org/llama.cppOther threatsAffected
  • <=b8227
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

If you cannot patch yet, restrict access to the llama-server service to trusted users and monitor for suspicious POST /completion requests containing crafted tool-id sequences.

Description

A use-after-free and double free vulnerability exists in llama.cpp before commit b11393 in the common_chat_peg_mapper::map function. This flaw allows unauthenticated remote attackers to corrupt heap memory by submitting a crafted POST /completion request with a dangling current_tool pointer. Exploitation can cause the llama-server to crash and potentially enable heap memory manipulation.

References

Community reviews

Loading reviews…