CVE-2026-55157 Token Optimizer MCP: OS command injection in smart_user via username in get-user-info
Attackers can execute arbitrary shell commands via the username argument in the smart_user tool of Token Optimizer MCP.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-55157?
CVE-2026-55157 is a high-severity command injection vulnerability in ooples token-optimizer-mcp, published on 28 Sep 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
Token Optimizer MCP measures token savings per AI coding agent, optimizes context, and shares a live local knowledge graph across 16 CLI clients. Prior to version 5.1.0, token-optimizer-mcp is vulnerable to OS command injection in the smart_user tool. Any MCP client that can call the smart_user tool can execute arbitrary shell commands through the username argument of the get-user-info operation. The commands execute with the privileges of the user running the token-optimizer-mcp server. This issue has been patched in version 5.1.0.
Weakness: CWE-78
Which versions are affected by CVE-2026-55157?
2 open source packages ship an affected version, including @ooples/token-optimizer-mcp.
| Package | Affected | Fixed in |
|---|---|---|
@ooples/token-optimizer-mcp npm | All versions | 5.1.0 |
@ooples/token-optimizer-mcp npm | All versions | 5.1.0 |
How do I fix CVE-2026-55157?
Upgrade @ooples/token-optimizer-mcp to 5.1.0 or later.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2026-55157 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-55157 exists.
Sources
Also known as GHSA-49mq-fc6q-3h46.