{"id":"CVE-2026-79745","aliases":["EUVD-2026-68689","GHSA-6cvf-cfch-4g7m"],"status":"published","title":"MCPHub: Missing Authorization on Built-in Prompt \u0026 Resource CRUD (Unauthorized Tampering of Globally-Served Templates/Resources)","description":"MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.","severity":{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.00439,"percentile":0.38449,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-862"],"published":"2026-08-31T17:56:17Z","modified":"2026-10-28T02:30:46Z","products":[{"vendor":"mcphub","product":"mcphub"},{"vendor":"samanhappy","product":"mcphub"}],"references":[{"url":"https://github.com/samanhappy/mcphub/security/advisories/GHSA-6cvf-cfch-4g7m","tags":["x_refsource_CONFIRM","exploit","advisory"]},{"url":"https://github.com/samanhappy/mcphub/pull/1069","tags":["x_refsource_MISC","fix"]},{"url":"https://github.com/samanhappy/mcphub/commit/6ba55ac63954a71506e61c088753251e2ff643cf","tags":["x_refsource_MISC","fix"]},{"url":"https://github.com/samanhappy/mcphub/releases/tag/v1.0.32","tags":["x_refsource_MISC","web"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/79xxx/CVE-2026-79745.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-79745","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-79745","title":"MCPHub: Missing Authorization on Built-in Prompt \u0026 Resource CRUD (Unauthorized Tampering of Globally-Served Templates/Resources)","description":"MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.","status":"published","published":"2026-08-31T17:56:17.622Z","modified":"2026-09-02T14:06:49.777Z","cvss":[{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L","level":"high","assessor":"cna"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T13:50:38.739766Z"}],"euvd":[{"id":"EUVD-2026-68689","description":"MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.","status":"published","published":"2026-08-31T17:56:17Z","modified":"2026-09-02T14:06:49Z","cvss":[{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L","level":"high"}],"updated_at":"2026-11-02T18:01:15.49101Z"}],"nvd":[{"id":"CVE-2026-79745","description":"MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.","status":"published","published":"2026-08-31T18:17:19.91Z","modified":"2026-09-08T21:08:37.32Z","cvss":[{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L","level":"high","assessor":"secondary"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T14:12:42.691315Z"}],"osv":[{"id":"CVE-2026-79745","title":"MCPHub: Missing Authorization on Built-in Prompt \u0026 Resource CRUD (Unauthorized Tampering of Globally-Served Templates/Resources)","description":"MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.","status":"published","published":"2026-08-31T17:56:17.622Z","modified":"2026-10-28T02:30:46.693804926Z","cvss":[{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L","level":"high"}],"cwes":["CWE-862"],"updated_at":"2026-11-02T15:45:17.44708Z"}]}}