Browse / Jailbreak and Guardrail Bypass / CVE-2026-12797
BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints
- Class
- Jailbreak and Guardrail Bypass (filed by a model that read the advisory)
- Technique
- Other weaknesses
- Also involves
- AI Framework and Platform Flaws
- Affected
- litellm (PyPI)
- Gets past
- Prompt guardrail or safety filter
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
BannedKeywords and Azure content safety guardrails are skipped on async endpoints because the hook's call type does not match, letting prompts pass unfiltered. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-12797
- https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a
- https://github.com/BerriAI/litellm
- https://vuldb.com/cve/CVE-2026-12797
- https://vuldb.com/submit/811288
- https://vuldb.com/vuln/372559
- https://vuldb.com/vuln/372559/cti
Source: GitHub Advisory Database, used under CC BY 4.0.