Skip to content

Hide Navigation Hide TOC

LibreChat MCP STDIO Argument Injection (CVE-2026-22252) - ATR-2026-00417 (3b6a0a8a-dd36-5f4b-88e0-b5d8c26e498d)

Detects exploitation of CVE-2026-22252 in LibreChat. The MCP STDIO adapter passes user-supplied tool arguments to child_process.spawn without quoting, allowing argv-level injection: an attacker supplies tool args containing shell-metacharacters or argument-separator sequences (e.g. ; curl evil, --option=$(id), \\n--exec=...) which the spawned process interprets as additional flags or shell commands. Part of the OX Security MCP-by-design batch (2026-04-15). Distinct from CVE-2026-40933 (config-time bypass) — this one targets the runtime argv channel.

Cluster A Galaxy A Cluster B Galaxy B Level
AI Model Inference API Access (90a420d4-3f03-4800-86c0-223c4376804a) MITRE ATLAS Attack Pattern LibreChat MCP STDIO Argument Injection (CVE-2026-22252) - ATR-2026-00417 (3b6a0a8a-dd36-5f4b-88e0-b5d8c26e498d) Agent Threat Rules 1
LibreChat MCP STDIO Argument Injection (CVE-2026-22252) - ATR-2026-00417 (3b6a0a8a-dd36-5f4b-88e0-b5d8c26e498d) Agent Threat Rules Command and Scripting Interpreter - T1059 (7385dfaf-6886-4229-9ecd-6fd678040830) Attack Pattern 1
LibreChat MCP STDIO Argument Injection (CVE-2026-22252) - ATR-2026-00417 (3b6a0a8a-dd36-5f4b-88e0-b5d8c26e498d) Agent Threat Rules Exploitation for Privilege Escalation - T1068 (b21c3b2d-02e6-45b1-980b-e69051040839) Attack Pattern 1
LibreChat MCP STDIO Argument Injection (CVE-2026-22252) - ATR-2026-00417 (3b6a0a8a-dd36-5f4b-88e0-b5d8c26e498d) Agent Threat Rules Indirect (a4a55526-2f1f-403b-9691-609e46381e17) MITRE ATLAS Attack Pattern 1
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Indirect (a4a55526-2f1f-403b-9691-609e46381e17) MITRE ATLAS Attack Pattern 2