CVE Intelligence
High

CVE-2025-0628 — Improper Authorization in BerriAI/litellm

An improper authorization vulnerability exists in the main-latest version of BerriAI/litellm. When a user with the role 'internal_user_viewer' logs into the application, they are provided with an overly privileged API key. This key can be used to access all the admin functionality of the application, including endpoints such as '/users/list' and '/users/get_users'. This vulnerability allows for privilege escalation within the application, enabling any account to become a PROXY ADMIN.

Published Mar 20, 2025 · Updated Oct 25, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: @huntr_ai

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.3% (30-day exploitation probability)+4
  • Technical severity (high)+6
  • CISA SSVC: exploitation "poc"+5

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.34%
ahead of 28% of scored CVEs · Oct 27, 2026
Affects
BerriAI
Litellm
CVSS base
8.1
High · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
No
can an attacker script the kill-chain steps
Technical impact
Total
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Pip Litellm: fixed in version 1.61.15 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (BerriAI Litellm, Pip Litellm).
  2. Apply the fixed version or the patch documented under Remediation.
  3. Search available logs for exploit probes, errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
BerriAI Litellm < v1.61.15-nightly Vulnerable CVE Program (cve.org) e CISA ADP
Pip Litellm < 1.61.15 Vulnerable GitHub Security Advisories

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
None

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
8.1 CVSS 3.0 High 2.8 5.2 security@huntr.dev via NIST National Vulnerability Database
8.1 CVSS 3.0 High — — GitHub, Inc. via GitHub Security Advisories
8.1 CVSS 3.0 High — — @huntr_ai via CVE Program (cve.org) e CISA ADP
CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N (score shown at the top: security@huntr.dev)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-266

Other CVEs with this weakness →

EPSS over time FIRST

Oct 25, 2026 → Oct 27, 2026 · 3 reading(s) · max 0.34%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
web/proxy/WAF logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first.

  • 2026
  • Fix documented
    Oct 25, 2026 · GitHub Security Advisories
  • Affected products added · pip/litellm
    Oct 25, 2026 · GitHub Security Advisories
  • Affected products added · berriai/berriai/litellm
    Oct 25, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 25, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 25, 2026
  • CVSS changed · 8.1
    Oct 25, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 25, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 25, 2026 · Alertas do Telegram
  • 2025
  • CVE published
    Mar 20, 2025 · @huntr_ai

Source activity

Repeated readings are counted rather than listed.

  • 2× References added · Oct 25, 2026 – Oct 25, 2026
  • 1× Official description updated · Oct 25, 2026 – Oct 25, 2026

References

4 on the record

Elsewhere on this site

BerriAI
every CVE for this vendor
CWE-266
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-114612 LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key 6d
  • CVE-2026-108575 BerriAI LiteLLM Secret Resolution main.py get_secret improper authorization 17d
  • CVE-2026-108574 BerriAI LiteLLM Spend Tracking spend_management_endpoints.py ui_view_session_spend_logs authorization 17d
  • CVE-2026-93355 LiteLLM Weak JWT Authentication via Email-Based User Lookup Sep 28, 2026
  • CVE-2026-89032 BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer Sep 25, 2026
  • CVE-2026-59823 LiteLLM: Server-side request forgery via the `user_config` request parameter in LiteLLM Proxy Sep 16, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2025-0628 is "Improper Authorization in BerriAI/litellm", rated High. It affects Litellm (BerriAI); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 8.1 describes technical severity. EPSS 0.34% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.