{"id":"CVE-2026-55157","title":"Token Optimizer MCP measures token savings per AI coding agent, optimizes context, and shares a live local knowledge graph across 16 CLI clients","summary":"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 sm…","severity":"high","cvss":8.4,"cvssVector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","cwe":["CWE-78"],"vendor":"ooples","product":"token-optimizer-mcp","affected":["token-optimizer-mcp < 5.1.0"],"patched":["@ooples/token-optimizer-mcp 5.1.0"],"published":"2026-09-28","updated":"2026-10-01","sourceUpdated":"2026-10-01T15:17:30.207","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-55157","references":[{"url":"https://github.com/ooples/token-optimizer-mcp/commit/b4ee96dac799cbfba0a9f9c17844ce9d613cbcc7","label":"security-advisories@github.com"},{"url":"https://github.com/ooples/token-optimizer-mcp/releases/tag/v5.1.0","label":"security-advisories@github.com"},{"url":"https://github.com/ooples/token-optimizer-mcp/security/advisories/GHSA-49mq-fc6q-3h46","label":"security-advisories@github.com"},{"url":"https://github.com/ooples/token-optimizer-mcp/security/advisories/GHSA-49mq-fc6q-3h46","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"},{"url":"https://github.com/advisories/GHSA-49mq-fc6q-3h46"}],"tags":["nvd","cve.org","exploit-available","ghsa","npm"],"exploitAvailable":true,"ssvc":{"exploitation":"poc","automatable":"no","technicalImpact":"total","timestamp":"2026-10-01T14:47:18.746481Z"},"epss":0.00881,"epssPercentile":0.58931,"aliases":["GHSA-49mq-fc6q-3h46"],"ecosystem":"npm","ingestedAt":"2026-08-14T22:21:25.769Z","slug":"CVE-2026-55157","body":"## Overview\n\nToken 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2026-55157)\n\nAffected packages:\n\n- `@ooples/token-optimizer-mcp < 5.1.0`\n\nPatched in:\n\n- `@ooples/token-optimizer-mcp 5.1.0`\n\nSource: https://github.com/advisories/GHSA-49mq-fc6q-3h46","depth":"midnight","depthScore":58,"depthScoreParts":{"impact":46.2,"likelihood":0.2,"exploitation":12,"ransomware":0},"changes":[{"seq":214338,"id":"CVE-2026-55157","ts":1790869740630,"field":"exploit_available","old":"false","new":"true"}]}