CVE-2026-42271: BerriAI LiteLLM

Should you act?

Exploited: patch now if you run it

CISA has confirmed exploitation in the wild. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

Yes, if you run BerriAI LiteLLM. CISA added this CVE to its Known Exploited Vulnerabilities catalog on 2026-06-08, which means there is reliable evidence of exploitation in the wild. US federal agencies must remediate by 2026-06-22; treat that as the outer limit, not the target.
EPSS 92.6%, percentile 99.8: FIRST’s model estimates a 92.6% chance of exploitation activity in the next 30 days, higher than 99.8% of all scored CVEs (very high). EPSS is a probability, not a verdict.
Needs an account (low (any account)). Exposure depends on who can log in.
Editorial verdict: Patch this week. LiteLLM Proxy: Three Exploited Flaws in CISA KEV — If you run a self-hosted LiteLLM Proxy older than 1.84.0, upgrade now and treat the provider keys it holds as possibly exposed; SDK-only users are not affected.

What it is

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.

CISA’s summary

BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.

Weakness type: CWE-77, CWE-78.

Product: BerriAI LiteLLM · Assigned by: GitHub_M · Published: 2026-05-08

Affected and fixed versions

Vendor	Product	Affected versions (per CVE record)
BerriAI	litellm	>= 1.74.2, < 1.83.7

Severity scores

Scored by	CVSS	Score	Vector
GitHub_M	4.0	8.7 High	`CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N`
redhat-SADP	3.1	8.8 High	`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H`

Attack vector: network (remotely reachable)
Attack complexity: low
Attack requirements: present (depends on deployment conditions)
Privileges required: low (any account)
User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

CISA KEV: added 2026-06-08; federal due date 2026-06-22. Known ransomware use: Unknown.
CISA required action: Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
CISA SSVC assessment: exploitation active, automatable no, technical impact total.
FIRST EPSS (model of 2026-10-21): 92.57% probability of exploitation activity in the next 30 days; percentile 99.8.

Timeline

2026-05-08 — CVE record published by GitHub_M
2026-06-08 — Added to CISA’s Known Exploited Vulnerabilities catalog
2026-06-22 — CISA remediation deadline for US federal agencies
2026-07-15 — CVE record last updated
2026-09-02 — erroneo.us brief: LiteLLM Proxy: Three Exploited Flaws in CISA KEV

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Other references from the CVE record and advisory

access.redhat.com access.redhat.com
RHBZ#2467924 bugzilla.redhat.com
security.access.redhat.com security.access.redhat.com

All exploited BerriAI vulnerabilities · Today’s Security Digest