Lucene search
+L

3 matches found

CVE
CVE
•added 2026/10/12 6:48 p.m.•39 views

CVE-2026-57143

The PraisonAI multi-agent system is vulnerable to Server-Side Request Forgery (SSRF) in the searxng_search and search_web tools within praisonaiagents versions prior to 1.6.62 . The root cause is the lack of validation for the searxng_url parameter, which is passed directly to requests.get(). Bec...

8.8CVSS5.9AI score
SaveExploits0References3
OSV
OSV
•added 2026/08/19 7:32 p.m.•15 views

GHSA-HJWH-XVFW-QRWJ SearXNG Basic Authentication Credentials Exposed Through MCP Logs and JSON-RPC Error Responses

Summary mcp-searxng version 1.11.0 exposes SearXNG Basic Authentication credentials embedded in the SEARXNGURL environment variable. When the server starts in STDIO mode and an MCP client connects, the complete SEARXNGURL, including its username and password, is sent to the client through an MCP...

5.5CVSS5.9AI score
SaveExploits0References3
Snyk
Snyk
•added 2026/06/18 2:27 p.m.•16 views

Server-side Request Forgery (SSRF)

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the searxngurl parameter in the searchweb and searxngsearch functions. An attacker can cause the server...

8.8CVSS5.9AI score
SaveExploits0References2
Rows per page
Query Builder