GHSA-p897-vf7j-f5h8 CVE-2026-12797 PYSEC-2026-4074
BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints
- Severity
- 0.0 / 10
- Medium · CVSS 4.0
- Exploit chance (EPSS)
- 0.40%
- Chance of exploitation in the next 30 days. Higher than 34.24% of scored vulnerabilities.
- Known exploited
- No
- Not in CISA's catalog
- Weakness
- CWE-285 Improper Authorization
- Fix
- None yet
- No fixed version published
Description
A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.
Affected versions
PyPI
| Package | Vulnerable | Fixed in |
|---|---|---|
| litellm | <= 1.82.5 |
No fix yet |
How to fix
No fixed version has been published yet. Until one is, remove or replace the package, or turn off or isolate the affected feature. This page updates when a fix ships.
Severity breakdown
CVSS 4.0 0.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- None
- Privileges required
- Low
- User interaction
- None
- Confidentiality (vulnerable system)
- Low
- Integrity (vulnerable system)
- Low
- Availability (vulnerable system)
- Low
- Confidentiality (subsequent systems)
- None
- Integrity (subsequent systems)
- None
- Availability (subsequent systems)
- None
- Exploit maturity
- Proof of concept
CVSS 3.1 6.3
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- Low
- Availability
- Low
Weakness
CWE-285: Improper Authorization
The product does not perform or incorrectly performs an authorization check when an actor attempts to access a resource or perform an action.
How to prevent it
- Architecture and Design: Divide the product into anonymous, normal, privileged, and administrative areas. Reduce the attack surface by carefully mapping roles with data and functionality. Use role-based access control (RBAC) to enforce the roles at the appropriate boundaries. Note that this approach may not protect against horizontal authorization, i.e., it will not protect a user from attacking others with the same role.
- Architecture and Design: Ensure that you perform access control checks related to your business logic. These checks may be different than the access control checks that you apply to more generic resources such as files, connections, processes, memory, and database records. For example, a database may restrict access for medical records to a specific database user, but each record might only be intended to be accessible to the patient and the patient's doctor.
- Architecture and Design: Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid. For example, consider using authorization frameworks such as the JAAS Authorization Framework [REF-233] and the OWASP ESAPI Access Control feature [REF-45].
- Architecture and Design: For web applications, make sure that the access control mechanism is enforced correctly at the server side on every page. Users should not be able to access any unauthorized functionality or information by simply requesting direct access to that page. One way to do this is to ensure that all pages containing sensitive information are not cached, and that all such pages restrict access to requests that are accompanied by an active and authenticated session token associated with a user who has the required permissions to access that page.
- System Configuration, Installation: Use the access control capabilities of your operating system and server environment and define your access control lists accordingly. Use a "default deny" policy when defining these ACLs.
References
Advisories
Packages
Other links
Timeline
- Published
- Last updated by the source
- Latest EPSS score
Related advisories
| Advisory | Severity | Why it's related |
|---|---|---|
| GHSA-7488-6r32-c95q LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback | High Known exploited | Also affects litellm |
| GHSA-v4p8-mg3p-g94g LiteLLM: Authenticated command execution via MCP stdio test endpoints | High Known exploited | Also affects litellm |
| GHSA-r75f-5x8p-qvmc LiteLLM has SQL Injection in Proxy API key verification | Critical Known exploited | Also affects litellm |
| GHSA-g5ff-637f-6q2m LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials` | High | Also affects litellm |
| GHSA-hhww-mrg2-969h LiteLLM vulnerable to reflected XSS in /sso/debug/callback | Medium | Also affects litellm |
| GHSA-7hp6-4w63-5g45 LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key | Critical | Also affects litellm |
| GHSA-hx8v-g79f-8w5f LiteLLM Proxy has server-side request forgery via the `user_config` request parameter | Medium | Also affects litellm |
| GHSA-3cv6-jpf6-8222 LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters | Medium | Also affects litellm |
MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.
Check your repos with MergeHarbor