CVE-2026-59821High· 7.2▾ TwilightLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by th…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 39.6 · likelihood 0.2 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Aug 7.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.4%
0.4% → 0.9%
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.
litellm < 1.82.0litellm = 1.82.0Upgrade past the affected range:
litellm 1.82.0Affected packages:
litellm < 1.82.0Patched in:
litellm 1.82.0Connected by shared product, vendor, weakness, or advisory.
GHSA-hhww-mrg2-969hMedium· 6.8LiteLLM vulnerable to reflected XSS in /sso/debug/callback
GHSA-g5ff-637f-6q2mHigh· 8.1LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
CVE-2026-114612Critical· 9.9LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key
CVE-2026-59823Medium· 5.3LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
CVE-2026-12799Medium· 4.3BerriAI litellm: UI User Enumeration leads to System-Wide Information Disclosure
CVE-2026-12796Medium· 6.3BerriAI litellm: SSO Login Does Not Invalidate Previous UI Session Tokens