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.
A SQL injection flaw in BerriAI's LiteLLM proxy server (AI Gateway) arises because the API key validation query used during proxy authentication checks concatenates the caller-supplied key into the SQL text rather than passing it as a bound parameter. An unauthenticated remote attacker can exploit this by sending a crafted Authorization header to any LLM API route, such as POST /chat/completions, reaching the query through the error-handling path, which can expose or modify data in the proxy's database and the credentials it manages.
Official description · NVDSource 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 NVD.
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.
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
74.8 / 100
Exploited
Yes, in CISA KEV
Reports
0
Tactics
3/15
How an attack unfolds
Based on MITRE ATT&CKA public catalogue of the techniques attackers use, maintained by MITRE. Patchfirst uses it to describe what attackers do with a vulnerability. mappings. Select a step to see the evidence.
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.
First seen exploited 11 days before it was disclosed. Public exploit code (Metasploit) was available 18 days before disclosure.
CISA KEV listing is when exploitation was confirmed, not necessarily the first attack.
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
3 TechniqueOne specific attacker behaviour in MITRE ATT&CK, such as T1190 “Exploit Public-Facing Application”. IDs with a dot, like T1059.004, are sub-techniques., grouped by TacticThe attacker’s goal at a stage of an attack in MITRE ATT&CK, such as Initial Access or Persistence. Each technique belongs to one or more tactics. in kill-chain order, 3 cited passagesAIAI-writtenWritten by a language model from the source data on this page. Not reviewed by a person.3
Initial AccessTA0001
Exploit Public-Facing ApplicationT1190Medium Confidence (technique links)How sure Patchfirst is that an ATT&CK technique applies to this CVE. High and medium links are shown by default; low ones come from early or generic mappings, text matching, or contradict the CVE’s details.
AI-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. claude-haiku-5-5: Unauthenticated crafted HTTP request to public-facing app.AI mapping from the description · how it is exploited
Unauthenticated crafted HTTP request to public-facing app
An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route
Data from Local SystemT1005Medium Confidence (technique links)How sure Patchfirst is that an ATT&CK technique applies to this CVE. High and medium links are shown by default; low ones come from early or generic mappings, text matching, or contradict the CVE’s details.
AI-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. claude-haiku-5-5: Attacker reads data from proxy database.AI mapping from the description · primary impact
Attacker reads data from proxy database
An attacker could read data from the proxy's database
Stored Data ManipulationT1565.001Medium Confidence (technique links)How sure Patchfirst is that an ATT&CK technique applies to this CVE. High and medium links are shown by default; low ones come from early or generic mappings, text matching, or contradict the CVE’s details.
AI-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. claude-haiku-5-5: Database modification via injected query.AI mapping from the description · primary impact
0 rules for this CVE · 169 general rules for its techniques
Rules for this CVE
0Sigma ruleAn open, vendor-neutral detection rule for log data. Security teams convert Sigma rules into searches for their own SIEM. that reference CVE-2026-42208 directly.
CVE-specific rules are not available in this build. Search SigmaHQ ↗
General rules for this CVE’s techniques
These detect the technique in general, not this specific vulnerability.
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.