SummaryAI-written · claude-haiku-5-5AI-written · claude-haiku-5-5Written by a language model from the source data on this page. Not reviewed by a person. Generated 29 Oct 2026.
The flaw is in BerriAI's LiteLLM, in its guardrails handling at the /guardrails/test_custom_code endpoint, which permits code injection through bytecode rewriting. An attacker with remote network access and low-privilege authentication, requiring no user interaction, can execute arbitrary code on the affected system.
Heading is the official description · CVE.orgSource dataSource dataCopied from an authoritative feed: NVD, CVE.org, CISA KEV, FIRST EPSS or MITRE CTID mappings, or labelled by the annotators of a published dataset. Copied from CVE.org.
Priority scorePatchfirst’s 0 to 100 ranking. It adds points for CISA KEV listing, ransomware use, EPSS, threat reports, public exploit code and CVSS. Every CVE page shows the breakdown.Breakdown
73.2 / 100
Exploited
Yes, in VulnCheck KEV
Reports
0
Tactics
0/15
Exploitation timelineDated milestones for a CVE: when it was disclosed, when exploit code became public, when exploitation was confirmed, and when threat reports named it.
Public exploit code (PoC-in-GitHub) appeared 39 days after disclosure. No confirmed exploitation is recorded.
MITRE ATT&CKA public catalogue of the techniques attackers use, maintained by MITRE. Patchfirst uses it to describe what attackers do with a vulnerability. techniques
No techniques linked
No ATT&CK techniques are linked to this CVE yet. MITRE CTID has not mapped it, and no report passage in the corpus ties it to a technique.
Am I affected? What do I upgrade to?
From GitHub Security Advisories and OSVSourceSource dataCopied from an authoritative feed: NVD, CVE.org, CISA KEV, FIRST EPSS or MITRE CTID mappings, or labelled by the annotators of a published dataset. GitHub Security Advisories and OSV.