Lucene search
K

16070 matches found

Vulnrichment
Vulnrichment
added 2026/05/12 4:25 p.m.6 views

CVE-2026-43992 JunoClaw: MCP write tools exposed raw BIP-39 mnemonic as a tool-call parameter

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

9.8CVSS5.8AI score0.00225EPSS
Exploits0References3
Microsoft Secure
Microsoft Secure
added 2026/05/12 3:0 p.m.8 views

Undermining the trust boundary: Investigating a stealthy intrusion through third-party compromise

In this article 1. Abuse of trusted relationships as an attack delivery mechanism 2. Methods, tools, and access strategies 3. Campaign conclusion 4. Microsoft Defender detection and hunting guidance In recent years, many sophisticated intrusions have increasingly avoided using noisy exploits,...

6.1AI score
Exploits0
Talos Blog
Talos Blog
added 2026/05/12 10:0 a.m.6 views

State-sponsored actors, better known as the friends you don’t want

State-sponsored actors don't break in. They log in, and they use your own tools to stay invisible for months. Responding to a state-sponsored threat is nothing like responding to ransomware, and the differences can make or break the outcome. From logging and baselines to OT segmentation and suppl...

5.9AI score
Exploits0
RedhatCVE
RedhatCVE
added 2026/05/12 8:20 a.m.6 views

CVE-2026-44694

n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. From version 2.18.7 to before version 2.50.2, there is an authenticated server-side request forgery vulnerability affecting the webhook trigger tools, the n8n API client N8NAPIURL, a...

9.1CVSS5.7AI score0.00235EPSS
Exploits0References1
Wiz blog
Wiz blog
added 2026/05/12 1:38 a.m.8 views

Mini Shai-Hulud Strikes Again: TanStack + more npm Packages Compromised

Detect and mitigate malicious npm packages linked to the latest Mini Shai-Hulud supply chain campaign targeting high-value developer tooling...

5.8AI score
Exploits0
Amd
Amd
added 2026/05/12 12:0 a.m.8 views

Unsafe OpenSSL Initialization Vulnerability Within AMD Manageability Software

CVE Details Refer to Glossary for explanation of terms CVE| CVE Description| CVSS Score ---|---|--- CVE-2025-62628| Unsafe OpenSSL initialization within some AMD optional tools may allow a local user-privileged attacker to inject a malicious DLL, potentially resulting in arbitrary code execution....

7CVSS6AI score0.00109EPSS
Exploits0
CNNVD
CNNVD
added 2026/05/12 12:0 a.m.8 views

Hugo 路径遍历漏洞

Hugo is a framework based on the Go language used by the Gohugoio community for quickly generating static websites. Versions of Hugo from 0.43 to 0.161.0 had a path traversal vulnerability. This vulnerability occurred due to the lack of restrictions on file system access when calling Node tools,...

8.6CVSS5.9AI score0.00274EPSS
Exploits0References1
vulnersOsv
vulnersOsv
added 2026/05/11 9:0 p.m.6 views

@antidrawapp/runtime (>=0.1.0 <=0.1.1), @ardeora/start-devtools (>=1.0.0 <=1.0.1) +99 more potentially affected by CVE-2026-45321 via @tanstack/history (>=1.0.0 <=1.15.13)

@tanstack/history NPM version =1.0.0, =0.1.0, =1.0.0, =0.6.2, =0.6.2, =0.1.1, =0.1.1, =0.6.2, =0.2.2, =0.3.0, =0.6.0, =0.2.2, =1.0.0, =1.0.9, =1.1.0, =1.1.2, =1.6.2 and more Source cves: CVE-2026-45321 Source advisory: SNYK:JS-TANSTACKHISTORY-16640204...

9.6CVSS8AI score0.01601EPSS
Exploits3
RedhatCVE
RedhatCVE
added 2026/05/11 8:26 p.m.6 views

CVE-2026-44336

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP Model Context Protocol server praisonai mcp serve registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a pat...

9.6CVSS6.3AI score0.00492EPSS
Exploits1References1
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/05/11 7:23 p.m.5 views

Malicious code in apkeep (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 d545ff7c3c178485cfb49d0028c4c808e67d0ee0fddcb4b7b195c943bb07d888 The package pretends to be a fork of a legitimate Rust library and uses the identity of the original authors. During usage, the obfuscated code targets...

5.8AI score
Exploits0References2
EUVD
EUVD
added 2026/05/11 6:31 p.m.19 views

EUVD-2026-29143

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

5.4CVSS5.8AI score0.00706EPSS
Exploits0References4
OSV
OSV
added 2026/05/11 6:31 p.m.4 views

GHSA-HP84-P2GQ-6FVR SQL injection vulnerability in pgAdmin 4 Maintenance Tool

SQL injection vulnerability in pgAdmin 4 Maintenance Tool. Four user-supplied JSON fields bufferusagelimit, vacuumparallel, vacuumindexcleanup, reindextablespace were concatenated directly into the rendered VACUUM/ANALYZE/REINDEX command and passed to psql --command. An authenticated user with th...

8.8CVSS6.2AI score0.00431EPSS
Exploits0References4
NVD
NVD
added 2026/05/11 6:16 p.m.10 views

CVE-2026-44998

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

5.4CVSS0.00706EPSS
Exploits0References3
NVD
NVD
added 2026/05/11 6:16 p.m.27 views

CVE-2026-42856

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to 5.1.3, the MCP HTTP transport accepts JSON-RPC tools/call requests with no authentication, session, origin, or token check, and dispatches them directly to the orchestrator's tool registry. The default bind address is 0.0.0.0. ...

8.7CVSS0.00471EPSS
Exploits0References1
ATTACKERKB
ATTACKERKB
added 2026/05/11 5:42 p.m.3 views

CVE-2026-42856

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to 5.1.3, the MCP HTTP transport accepts JSON-RPC tools/call requests with no authentication, session, origin, or token check, and dispatches them directly to the orchestrator's tool registry. The default bind address is 0.0.0.0. ...

8.7CVSS5.8AI score0.00471EPSS
Exploits0References2Affected Software1
Snyk
Snyk
added 2026/05/11 5:19 p.m.11 views

Information Exposure

Overview mediawiki/core is a Free software wiki application developed by the Wikimedia Foundation and others. Note: This package is not maintained on Packagist anymore, but newer releases exist. Affected versions of this package are vulnerable to Information Exposure via the includes/Skin/Skin.Ph...

7.5CVSS5.8AI score0.00237EPSS
Exploits0References2
ATTACKERKB
ATTACKERKB
added 2026/05/11 4:46 p.m.4 views

CVE-2026-44998

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

5.4CVSS5.8AI score0.00706EPSS
Exploits0References4
Cvelist
Cvelist
added 2026/05/11 4:46 p.m.30 views

CVE-2026-44998 OpenClaw < 2026.4.20 - Tool Policy Bypass via Bundled MCP/LSP Tools

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

5.4CVSS0.00706EPSS
Exploits0References3
Vulnrichment
Vulnrichment
added 2026/05/11 4:46 p.m.4 views

CVE-2026-44998 OpenClaw < 2026.4.20 - Tool Policy Bypass via Bundled MCP/LSP Tools

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

5.4CVSS5.8AI score0.00706EPSS
Exploits0References3
CVE
CVE
added 2026/05/11 4:46 p.m.16 views

CVE-2026-44998

OpenClaw prior to version 2026.4.20 contains a tool policy bypass vulnerability in which bundled MCP and LSP tools can be appended to the effective tool set after policy filtering. This allows attackers with local agent access to bypass profile policies, allow/deny lists, owner-only restrictions,...

5.4CVSS5.8AI score0.00706EPSS
Exploits0References3Affected Software1
Rows per page
Query Builder