Detect BerriAI LiteLLM SQL Injection Exploitation (CVE-2026-42208) in Sumo Logic CSE
Detects exploitation attempts targeting a SQL injection vulnerability in BerriAI LiteLLM (CVE-2026-42208, CWE-89). LiteLLM is a widely deployed LLM proxy/gateway; successful exploitation allows unauthenticated or authenticated attackers to manipulate backend database queries, potentially exfiltrating API keys, user data, model configurations, and spend tracking records. This CVE is listed on the CISA KEV catalog, indicating active exploitation in the wild.
MITRE ATT&CK
Sumo Detection Query
_sourceCategory=web/access OR _sourceCategory=proxy/logs OR _sourceCategory=waf
| where %"cs-uri-stem" matches /\/(key|user|spend|model|team|chat\/completions)\//
| where (
%"cs-uri-query" matches /(?i)('\s*OR\s*'|UNION\s+SELECT|--\s|%27|0x27|1=1)/
or _raw matches /(?i)('\s*OR\s*'|UNION\s+SELECT|'\s*;--|1\s*=\s*1)/
)
| parse regex field=_raw "(?<src_ip>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})"
| parse regex field=_raw "\"(?<user_agent>[^\"]+)\"\s*$"
| timeslice 1m
| stats count as attempt_count, values(%"cs-uri-stem") as paths by src_ip, user_agent, _timeslice
| where attempt_count >= 1
| sort by attempt_count descSumo Logic query for detecting SQL injection attempts against LiteLLM API routes, parsing web access logs for SQLi patterns in URI query strings and raw HTTP request bodies.
Data Sources
Required Tables
False Positives & Tuning
- Automated API clients sending URL-encoded content with apostrophes
- Security scanning tools during scheduled assessments
- LLM model responses that are URL-encoded and logged by the proxy
- Developer testing with hand-crafted SQL-like API payloads
Other platforms for CVE-2026-42208
Testing Methodology
Validate this detection against 4 adversary techniques from Atomic Red Team. Each test below lists the behaviour to exercise and the telemetry you should expect to see. Executable commands and cleanup steps are available with Pro.
- Test 1Error-Based SQL Injection on LiteLLM /key/info Endpoint
Expected signal: HTTP 500 or 422 response from LiteLLM; database error message in application logs; WAF alert if deployed
- Test 2UNION SELECT Injection Attempt on /user/info Endpoint
Expected signal: HTTP 500 or data leak in response body; PostgreSQL logs show UNION SELECT statement; network proxy logs capture full URL with UNION payload
- Test 3Time-Based Blind SQL Injection via LiteLLM /spend/logs
Expected signal: Response time >= 5 seconds; PostgreSQL slow query log entry for pg_sleep; application logs show extended request duration
- Test 4POST Body SQL Injection to LiteLLM /key/generate
Expected signal: HTTP 400/500 with SQL error in response; application log shows malformed query; SIEM alert on POST body containing OR 1=1
Unlock Pro Content
Get the full detection package for CVE-2026-42208 including response playbook, investigation guide, and atomic red team tests.