Is dev.langchain4j:langchain4j-pgvector safe?

GHSA-2mfg-cc43-9pcj

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 and removeAll(Filter) operations.

pgvector — JSON mode (default, COMBINEDJSON / COMBINEDJSONB). JSONFilterMapper places the key inside a single-quoted SQL literal (the JSON key of the ->> operator) with no escaping:

(metadata->>'')::text

A key containing a single quote breaks out, e.g. metadataKey("')::text IS NOT NULL OR pgsleep(1) IS NOT NULL --") injects a live pgsleep(1) (observable as a delay; exploitable for blind data extraction).

pgvector — column mode (COLUMNPERKEY). ColumnFilterMapper used the key as a bare, unquoted, unvalidated SQL identifier (::), so a key such as 1=1 OR true -- injects directly.

MariaDB — JSON mode (default). JSONFilterMapper placed the key inside the JSON path literal '$.' 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 (COLUMNPERKEY). 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.

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.

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 PostgreSQL standardconformingstrings = 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.

• Do not pass untrusted input as metadata filter keys.
• Restrict filter keys to a known allow-list at the application layer.

• pgvector: JSONFilterMapper, ColumnFilterMapper
• MariaDB: JSONFilterMapper, MariaDbFilterMapper, ColumnFilterMapper