Summary
LangChain4j: SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector
The MariaDB and pgvector embedding stores build metadata-filter SQL by string-concatenating
filter keys (and, in MariaDB, string values) directly into the query without adequate
escaping. A crafted metadata key in EmbeddingSearchRequest.filter() can break out of its SQL
context and inject arbitrary SQL into the statements executed by the stores' search andremoveAll(Filter) operations.
Details
pgvector, JSON mode (default, COMBINED_JSON / COMBINED_JSONB). JSONFilterMapper
places the key inside a single-quoted SQL literal (the JSON key of the ->> operator) with no
escaping:
(metadata->>'<key>')::text
A key containing a single quote breaks out, e.g.metadataKey("')::text IS NOT NULL OR pg_sleep(1) IS NOT NULL --") injects a live pg_sleep(1)
(observable as a delay; exploitable for blind data extraction).
pgvector, column mode (COLUMN_PER_KEY). ColumnFilterMapper used the key as a bare,
unquoted, unvalidated SQL identifier (<key>::<type>), so a key such as 1=1 OR true --
injects directly.
MariaDB, JSON mode (default). JSONFilterMapper placed the key inside the JSON path literal'$.<key>' unescaped (same break-out mechanism). Additionally, MariaDbFilterMapper.formatValue()
escaped ' but not \; because MariaDB treats backslash as an escape character by default, a
string value ending in a backslash could also break out of its literal.
MariaDB, column mode (COLUMN_PER_KEY). ColumnFilterMapper fell back to the raw,
unescaped key when the driver could not quote it as an identifier (e.g. a
character).
The filter key is the runtime injection surface; both stores' search() (including pgvector's
HYBRID mode) and removeAll(Filter) are affected. Add/upsert operations a
parameterized and not affected.
Workarounds
- Do not pass untrusted input as metadata filter keys.
- Restrict filter keys to a known allow-list at the application layer.
References
- pgvector:
JSONFilterMapper,ColumnFilterMapper - MariaDB:
JSONFilterMapper,MariaDbFilterMapper,ColumnFilterMapper
Impact
Applications that allow attacker-influenced metadata filter keys (e.g. use
LLM-generated filters) to reach these stores are exposed to SQL injection: blind data
exfiltration, denial of service via sleep functions, and, through `remove
deletion of arbitrary rows. Applications using only hard-coded, developer-defined filter keys
are not reachable.
Untrusted input alters a database query, allowing the attacker to read or modify data the query was not intended to access. Typical impact: data disclosure or modification.
CVE-2026-55405 has a CVSS score of 7.6 (High). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, 1.16.3-beta26); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Fixed in langchain4j-mariadb and langchain4j-pgvector 1.16.3-beta26:
- JSON filter keys are escaped before being embedded in the SQL string lit
quotes doubled, correct for PostgreSQLstandard_conforming_strings = on; MariaDB: backslash
and single quote). - MariaDB string values escape both
\and'. - Column-mode keys are validated/quoted as identifiers and rejected when u
concatenated as raw SQL.
Frequently Asked Questions
- What is CVE-2026-55405? CVE-2026-55405 is a high-severity SQL injection vulnerability in dev.langchain4j:langchain4j-mariadb (maven), affecting versions <= 1.2.0-beta8. It is fixed in 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, 1.16.3-beta26. Untrusted input alters a database query, allowing the attacker to read or modify data the query was not intended to access.
- How severe is CVE-2026-55405? CVE-2026-55405 has a CVSS score of 7.6 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which packages are affected by CVE-2026-55405?
dev.langchain4j:langchain4j-mariadb(maven) (versions <= 1.2.0-beta8)dev.langchain4j:langchain4j-pgvector(maven) (versions <= 1.2.0-beta8)
- Is there a fix for CVE-2026-55405? Yes. CVE-2026-55405 is fixed in 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, 1.16.3-beta26. Upgrade to this version or later.
- Is CVE-2026-55405 exploitable, and should I be worried? Whether CVE-2026-55405 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-55405 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-55405?
- Upgrade
dev.langchain4j:langchain4j-mariadbto 1.2.1-beta8 or later - Upgrade
dev.langchain4j:langchain4j-mariadbto 1.5.1-beta11 or later - Upgrade
dev.langchain4j:langchain4j-mariadbto 1.11.8-beta19 or later - Upgrade
dev.langchain4j:langchain4j-mariadbto 1.16.3-beta26 or later - Upgrade
dev.langchain4j:langchain4j-pgvectorto 1.2.1-beta8 or later - Upgrade
dev.langchain4j:langchain4j-pgvectorto 1.5.1-beta11 or later - Upgrade
dev.langchain4j:langchain4j-pgvectorto 1.11.8-beta19 or later - Upgrade
dev.langchain4j:langchain4j-pgvectorto 1.16.3-beta26 or later
- Upgrade