Lucene search
+L

72 matches found

Vulnrichment
Vulnrichment
•added 2026/08/25 2:33 p.m.•8 views

CVE-2026-55531 PraisonAI: Unauthenticated unbounded session accumulation in the PraisonAI MCP HTTP server (memory exhaustion; session TTL never enforced)

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcppost handler creates a new sessions entry for every initialize request but does not call cleanupsessions or enforce a maximum. An unauthenticated caller can exhaust memory. The fix invokes cleanup and limit...

6.5CVSS5.9AI score0.00452EPSS
SaveExploits0References3
CVE
CVE
•added 2026/08/25 2:33 p.m.•47 views

CVE-2026-55531

PraisonAI 's MCP HTTP Stream server (prior to 4.6.58 ) suffers from unbounded in-memory session accumulation. Each unauthenticated initialize request creates a new entry in the _sessions dictionary, but the existing _cleanup_sessions method is never invoked and no maximum session cap is enforced,...

6.5CVSS5.9AI score0.00452EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/08/25 2:33 p.m.•44 views

CVE-2026-55531 PraisonAI: Unauthenticated unbounded session accumulation in the PraisonAI MCP HTTP server (memory exhaustion; session TTL never enforced)

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcppost handler creates a new sessions entry for every initialize request but does not call cleanupsessions or enforce a maximum. An unauthenticated caller can exhaust memory. The fix invokes cleanup and limit...

6.5CVSS0.00452EPSS
SaveExploits0References3
Vulnrichment
Vulnrichment
•added 2026/08/25 2:26 p.m.•9 views

CVE-2026-55529 PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

6.9CVSS5.9AI score0.00175EPSS
SaveExploits0References3
Mend
Mend
•added 2026/08/25 2:26 p.m.•4 views

CVE-2026-55529

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

7.1CVSS0.00175EPSS
SaveExploits0References8
CVE
CVE
•added 2026/08/25 2:26 p.m.•104 views

CVE-2026-55529

PraisonAI (a multi-agent teams system) has an origin validation bypass in its MCP HTTP Stream transport. The _validate_origin method uses request_origin.startswith(allowed), so an attacker-controlled origin like http://localhost.evil.example matches the http://localhost allowlist entry via prefix...

6.9CVSS5.9AI score0.00175EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/08/25 2:26 p.m.•40 views

CVE-2026-55529 PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

6.9CVSS0.00175EPSS
SaveExploits0References3
EUVD
EUVD
•added 2026/08/25 2:26 p.m.•14 views

EUVD-2026-65496

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

6.9CVSS5.9AI score0.00175EPSS
SaveExploits0References3
OSV
OSV
•added 2026/08/25 2:26 p.m.•17 views

CVE-2026-55529 PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

6.9CVSS5.6AI score
SaveExploits0References5
OSV
OSV
•added 2026/08/25 2:26 p.m.•14 views

GHSA-WJ6G-V78P-6FX3 PraisonAI has an origin validation bypass in MCP HTTP Stream transport that allows browser-mediated unauthenticated tool execution on local MCP server

Summary PraisonAI's MCP HTTP Stream transport uses an unsafe prefix match when validating the Origin header. The default localhost allowlist includes origins such as http://localhost, and the validation accepts any origin that starts with an allowed value. As a result, an attacker-controlled orig...

6.9CVSS5.8AI score0.00175EPSS
SaveExploits0References4
Github Security Blog
Github Security Blog
•added 2026/08/25 2:26 p.m.•21 views

PraisonAI has an origin validation bypass in MCP HTTP Stream transport that allows browser-mediated unauthenticated tool execution on local MCP server

Summary PraisonAI's MCP HTTP Stream transport uses an unsafe prefix match when validating the Origin header. The default localhost allowlist includes origins such as http://localhost, and the validation accepts any origin that starts with an allowed value. As a result, an attacker-controlled orig...

6.9CVSS5.8AI score0.00175EPSS
SaveExploits0References4Affected Software1
Positive Technologies
Positive Technologies
•added 2026/08/25 12:00 a.m.•31 views

PT-2026-81320

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.58 Description The MCP HTTP Stream transport in PraisonAI uses an unsafe prefix match when validating the Origin header via the validate origin method. The validation logic accepts any origin that starts with an...

6.9CVSS5.8AI score0.00175EPSS
SaveExploits0References12
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/25 12:00 a.m.•6 views

CVE-2026-55529: Missing Authentication for Critical Function

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

6.9CVSS5.9AI score0.00175EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/08/25 12:00 a.m.•26 views

PT-2026-81345

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.58 Description A Cross-Site Request Forgery CSRF issue exists in the MCP HTTP-stream transport. The validate origin function in transports/http stream.py uses a prefix match via startswith to validate the reques...

7.6CVSS5.8AI score0.00197EPSS
SaveExploits0References11
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/25 12:00 a.m.•5 views

CVE-2026-55532: Origin Validation Error

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

7.6CVSS5.8AI score0.00197EPSS
SaveExploits0References3
Vulnrichment
Vulnrichment
•added 2026/08/21 12:07 p.m.•16 views

CVE-2026-59279 Unbounded persistent session allocation via repeated initialize requests

The MCP Streamable HTTP server transport WebFlux and WebMvc variants does not place any limit on the number of sessions it retains, and by default does not require clients to be authenticated. As a result, a remote attacker can cause the server to accumulate an unbounded number of sessions over...

7.5CVSS6AI score0.00549EPSS
SaveExploits0References1
NVD
NVD
•added 2026/08/12 5:17 p.m.•18 views

CVE-2026-73296

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, createmobiledatacollectionserver and createmobileactionserver in ufo/client/mcp/httpservers/mobilemcpserver.py exposed Streamable HTTP MCP services on TCP ports 8020 and 8021 without...

9.4CVSS0.03652EPSS
SaveExploits0References3
EUVD
EUVD
•added 2026/08/12 4:29 p.m.•20 views

EUVD-2026-57323

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, createmobiledatacollectionserver and createmobileactionserver in ufo/client/mcp/httpservers/mobilemcpserver.py exposed Streamable HTTP MCP services on TCP ports 8020 and 8021 without...

9.4CVSS5.3AI score0.03652EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/02 12:00 a.m.•7 views

CVE-2026-68578: Missing Authentication for Critical Function

ArcadeDB versions before 26.7.3 fail to bind the authenticated principal in the MCP HTTP transport, causing all engine permission checks to silently pass as no-ops. Non-root MCP-allowed users can perform arbitrary database writes, DDL, schema mutations, and execute arbitrary JavaScript code via t...

7.7CVSS6.1AI score0.00363EPSS
SaveExploits0References2
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/07/31 9:53 p.m.•25 views

Malicious code in kip-mcp-http (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector dd2c47d8520d4f3bbff232ba1143fdbf7f64f1fa31a70f91be117714d19455e2 lib/report.js imports childprocess, fs, https, and os and, via execSync plus fs.readFileSync calls, gathers host identifiers os.hostname, os.userInfo...

5.6AI score
SaveExploits0References2
Rows per page
Query Builder