Skip to content

Hide Navigation Hide TOC

Spring AI MilvusVectorStore Filter Expression Injection (CVE-2026-41705) - ATR-2026-00448 (f80b4ef8-3e79-547e-b7d9-b3864a466ddd)

Detects exploitation of CVE-2026-41705 (High), filter-expression injection in Spring AI's MilvusVectorStore. The vulnerable sink concatenates a user/LLM-controlled fragment into a Milvus DSL filter expression passed to MilvusVectorStore.delete() or .similaritySearch() without quoting or parameterisation. Attacker-controlled input breaks out of the intended clause and injects new Milvus DSL operators ( == , in[ , like ), boolean combinators ( or , and ), trailing terminators ( ; -- ), or escape bypasses ( like '%' ESCAPE '\' ) to broaden the deletion / retrieval scope, exfiltrate or wipe arbitrary collection entries, or bypass access-control filters baked into the original expression. This rule detects the LLM-output / user-input payload shapes that reach the Milvus filter sink: filter-context fields containing unbalanced quotes, Milvus operators combined with boolean chaining, or known filter-bypass primitives. CWE-89, CWE-1287. Patches in Spring AI >= 1.0.0; this rule detects exploit attempts against unpatched deployments and provides defence-in-depth post-patch by catching the injection payload shape regardless of upstream patch state.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Spring AI MilvusVectorStore Filter Expression Injection (CVE-2026-41705) - ATR-2026-00448 (f80b4ef8-3e79-547e-b7d9-b3864a466ddd) Agent Threat Rules 1
Spring AI MilvusVectorStore Filter Expression Injection (CVE-2026-41705) - ATR-2026-00448 (f80b4ef8-3e79-547e-b7d9-b3864a466ddd) Agent Threat Rules Exploit Public-Facing Application - T1190 (3f886f2a-874f-4333-b794-aa6075009b1c) Attack Pattern 1