Lucene search
+L

7 matches found

OSV
OSV
•added 2026/09/15 5:46 p.m.•21 views

CVE-2026-54688 mcp-searxng: SSRF in web_url_read: the internal-address guard is disabled by default (MCP_HTTP_HARDEN off)

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.2.0, weburlread passes a caller-supplied URL to the server-side fetch path while assertUrlAllowed in src/url-reader.ts runs only when MCPHTTPHARDEN is enable...

6.5CVSS5.7AI score
SaveExploits0References6
Cvelist
Cvelist
•added 2026/09/15 5:46 p.m.•43 views

CVE-2026-54688 mcp-searxng: SSRF in web_url_read: the internal-address guard is disabled by default (MCP_HTTP_HARDEN off)

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.2.0, weburlread passes a caller-supplied URL to the server-side fetch path while assertUrlAllowed in src/url-reader.ts runs only when MCPHTTPHARDEN is enable...

6.5CVSS0.00499EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/09/15 5:46 p.m.•11 views

CVE-2026-54688 mcp-searxng: SSRF in web_url_read: the internal-address guard is disabled by default (MCP_HTTP_HARDEN off)

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.2.0, weburlread passes a caller-supplied URL to the server-side fetch path while assertUrlAllowed in src/url-reader.ts runs only when MCPHTTPHARDEN is enable...

6.5CVSS5.7AI score0.00499EPSS
SaveExploits0References4
Patchstack
Patchstack
•added 2026/08/19 7:23 p.m.•13 views

NPM: SearXNG MCP Server is Vulnerable to SSRF in web_url_read: the internal-address guard is disabled by default (MCP_HTTP_HARDEN off)

NPM: SearXNG MCP Server is Vulnerable to SSRF in weburlread: the internal-address guard is disabled by default MCPHTTPHARDEN off vulnerability discovered by ? in WordPress Npm mcp-searxng versions 1.2.1...

5.3AI score0.00499EPSS
SaveExploits0References4Affected Software1
CVE
CVE
•added 2026/07/07 9:20 p.m.•56 views

CVE-2026-54607

FastGPT exposed an SSRF issue in the HTTP-tool OpenAPI schema importer prior to 4.15.0-beta4. The importer validates only the top-level URL before handing refs to SwaggerParser.bundle, whose resolver can fetch and inline $ref URLs bypassing FastGPT’s internal-address guard, enabling an authentica...

7.7CVSS6AI score0.00523EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/07/07 9:20 p.m.•12 views

CVE-2026-54607 FastGPT: SSRF in HTTP-tool OpenAPI schema importer via SwaggerParser $ref (bypasses the isInternalAddress guard)

FastGPT is a knowledge-based AI application platform. Prior to 4.15.0-beta4, the HTTP-tool OpenAPI schema importer validates only the top-level URL before passing it to SwaggerParser.bundle, whose remote reference resolver fetches $ref URLs without FastGPT's internal-address guard and returns...

7.7CVSS6AI score0.00523EPSS
SaveExploits0References4
RedhatCVE
RedhatCVE
•added 2026/05/11 8:27 p.m.•21 views

CVE-2026-44286

FastGPT is an AI Agent building platform. Prior to version 4.14.17, an unauthenticated Server-Side Request Forgery SSRF vulnerability allows attackers or authenticated users with App editing privileges to send arbitrary HTTP requests to internal/private network addresses. The fetchData function i...

2.3CVSS5.9AI score0.00387EPSS
SaveExploits0References1
Rows per page
Query Builder