CVE-2026-12797
Access Control in Litellm ≤ 1.82.5
Raw vector
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/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-12797 is a low-severity Improper Authorization (CWE-285) vulnerability in Litellm Litellm. Its CVSS base score is 2.1 (Low).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 33th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and AC-4 (Information Flow Enforcement) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-38156
Vulnerability Data
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…
more
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.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Remote authorization bypass in public Completions Interface directly enables exploitation of the exposed application.
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
Mitigating Controls (NIST 800-53 r5) AI
Directly enforces authorization decisions on the prompt argument before the completions hook proceeds, blocking the CWE-863 bypass.
Enforces information flow rules based on content (banned keywords) so that manipulated prompts cannot circumvent the enterprise hook.
Validates and sanitizes untrusted prompt input to the async_pre_call_hook, preventing malformed data from triggering incorrect authorization.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.AA-05 mostly prevents CWE-285 via enforced policy, reviews, and least-privilege authorization decisions, yet CWE-285 remains only partially prevented because code-level check omissions or errors can still occur outside that single control.
Secure SDLC practices catch and eliminate most authorization defects before release, yet a single broad outcome cannot address every design, role, and runtime facet of CWE-285.
PR.AA-01 supplies managed identities and access-request workflows that can support downstream authorization decisions, yet does nothing to enforce or verify authorization checks inside a product, leaving CWE-285 fully unaddressed by this control alone.
Network segmentation/zero-trust limits external reachability (partial prevention of exploitation) but leaves application-level authorization logic untouched, so the CWE remains fully introducible and only one facet of its risk is addressed.
PR.PS-05 blocks unauthorized binaries/DNS while CWE-285 is an in-product authorization-check defect, so the control neither prevents the weakness nor removes any of its risk.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Granular, policy-driven assignment of permissions and dynamic enforcement of those permissions prevent the incorrect or missing authorization decisions that lead to improper authorization flaws.
By requiring documented authorization rules and periodic policy reviews, the control makes it less likely that authorization decisions will be omitted or implemented inconsistently across applications.
Mapping access rights to information classification and business requirements forces correct enforcement of authorization decisions, blocking the incorrect authorization weakness at the policy and implementation stage.
Enforcing policy-driven approval and role-change reviews stops incorrect or stale authorization decisions from remaining in effect after job changes or terminations.
Independent reviewers evaluate whether authorization logic matches policy, thereby reducing the window in which incorrect or missing authorization checks remain in production.
By requiring managers to verify that authorization decisions match policy and to remediate deviations, the control limits the persistence of incorrect or missing authorization checks.