CVE-2025-55178 json
Llama Stack could potentially allow for remote code execution
published last yr. modified 4mo ago also GHSA-x75h-m6jj-6cj2 , PYSEC-2026-1571 , EUVD-2025-31066
- cvss
- 5.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 43%
- public exploits
- 0
- none known
Summary
Llama Stack prior to version v0.2.20 accepted unverified parameters in the resolve_ast_by_type function which could potentially allow for remote code execution.
Patch / fix
- pypi llama-stack 0.2.20
- Meta Platforms, Inc Llama Stack 0.2.20
Is CVE-2025-55178 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerVendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2025-55178 updated cvss 5.3
llama-stack: llama stack unverified input
-
Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9affected: workaround, no fix available “Fix deferred”
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- total
- Assessed
- last yr.
Exploit prediction
0.50% chance of exploitation in the next 30 days, higher than 43% of all scored CVEs (FIRST EPSS, 2026-11-09).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CISA ADP | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
| CNA | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
| OSV | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
| GitHub | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | llama-stack | <0.2.20 |
0.2.20 |
Affected products
- Meta Platforms, Inc Llama Stack
Classification
- Weakness
-
- CWE-20 Improper Input Validation
References
-
github.com
/llamastack/llama-stack/pull/3281
web
-
github.com
/llamastack/llama-stack/commit/efdb5558b8dcab4d141678bfed0a405e2f312b6f
web
-
facebook.com
/security/advisories/cve-2025-55178
web
-
github.com
/llamastack/llama-stack/releases/tag/v0.2.20
web
-
nvd.nist.gov
/vuln/detail/CVE-2025-55178
advisory
-
github.com
/llamastack/llama-stack
package
-
pypi.org
/project/llama-stack
package
-
github.com
/advisories/GHSA-x75h-m6jj-6cj2
advisory
Sources
- CVE List CVE-2025-55178
- GitHub Advisory GHSA-x75h-m6jj-6cj2
- NVD CVE-2025-55178
- OSV PYSEC-2026-1571
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.