CVE-2026-12797
published 2026-06-21CVE-2026-12797: 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…
PriorityP345medium6.3CVSS 3.1
AVNACLPRLUINSUCLILAL
EPSS
0.23%
13.2th percentile
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
13 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| ansible-automation-platform-26 | lightspeed-chatbot-rhel9 | — | — |
| ansible-automation-platform-27 | lightspeed-chatbot-rhel9 | — | — |
| berriai | litellm | — | — |
| berriai | litellm | — | — |
| berriai | litellm | — | — |
| berriai | litellm | — | — |
| berriai | litellm | — | — |
| berriai | litellm | — | — |
| exploit-intelligence-tech-preview | vulnerability-analysis-rhel9 | — | — |
| litellm | litellm | <= 1.82.5 | — |
| rhoai | odh-llama-stack-core-rhel9 | — | — |
| rhoai | odh-mlflow-rhel9 | — | — |
| rhoai | odh-trustyai-garak-lls-provider-dsp-rhel9 | — | — |
CVSS provenance
nvdv3.16.3MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
nvdv4.02.1LOWCVSS: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:X
nvdv2.06.5MEDIUMAV:N/AC:L/Au:S/C:P/I:P/A:P
vendor_redhat6.3MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
Red Hat
litellm: BerriAI litellm: Incorrect authorization via prompt manipulation
vendor_redhat·2026-06-21·CVSS 6.3
CVE-2026-12797 [MEDIUM] CWE-551 litellm: BerriAI litellm: Incorrect authorization via prompt manipulation
litellm: BerriAI litellm: Incorrect authorization via prompt manipulation
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.
A flaw was found in BerriAI litellm. A remote attacker could manipulate the `prompt` argument in the `async_pre_call_hook` function of the Completions Interface component. This manipulation leads to incorrect authorization, potentially allowing the attacker to bypass
GHSA
A security flaw has been discovered in BerriAI litellm up to 1.82.5.
ghsa_unreviewed·2026-06-21
CVE-2026-12797 [LOW] CWE-285 A security flaw has been discovered in BerriAI litellm up to 1.82.5.
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.
VulDB
BerriAI litellm up to 1.82.5 Completions Interface banned_keywords.py async_pre_call_hook prompt authorization
vuldb·2026-06-20
CVE-2026-12797 [CRITICAL] BerriAI litellm up to 1.82.5 Completions Interface banned_keywords.py async_pre_call_hook prompt authorization
A vulnerability was found in BerriAI litellm up to 1.82.5 and classified as critical. 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.
This vulnerability was named CVE-2026-12797. The attack may be performed from remote. In addition, an exploit is available.
The vendor was contacted early about this disclosure.
No detection rules found.
No public exploits indexed.
2026-06-21
Published