VulnWatch VulnWatch
← Back to dashboard
#

Agentic / MCP

204 entries

Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.

Subscribe to this tag's RSS feed

Critical nvd

CVE-2026-43992: JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool (send_tokens,

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool (send_tokens, execute_contract, instantiate_contract, upload_wasm, ibc_transfer, etc.) accepte...

Agentic / MCP agentic llm
9.8
CVSS
1 month ago
High nvd

CVE-2026-43991: JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, substring-based blocklist in plugin

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, substring-based blocklist in plugin-shell's command-safety check could be bypassed by adversarial argument construc...

Agentic / MCP adversarial agentic
8.4
CVSS
1 month ago
High nvd

CVE-2026-43990: JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, plugin-shell's run_command wrapped

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, plugin-shell's run_command wrapped every agent-supplied command in 'sh -c' / 'cmd /C' and passed the full argument...

8.4
CVSS
1 month ago
High nvd

CVE-2026-43989: JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, the upload_wasm MCP tool accepted a

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, the upload_wasm MCP tool accepted a filesystem path from the agent and uploaded whatever bytes the path resolved to...

8.5
CVSS
1 month ago
Unknown nvd

CVE-2025-65719: An issue in Open Source Kubectl MCP Server v1.1.1 allows attackers to execute arbitrary code on a victim system via user

An issue in Open Source Kubectl MCP Server v1.1.1 allows attackers to execute arbitrary code on a victim system via user interaction with a crafted HTML page.

Agentic / MCP mcp server
1 month ago
High nvd

CVE-2026-42260: Open-WebSearch is a multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval. Prior to

Open-WebSearch is a multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval. Prior to 2.1.7, isPublicHttpUrl / assertPublicHttpUrl in src/utils/urlSafety.ts do not re...

8.2
CVSS
1 month ago
Unknown rss_thehackernews

Why Agentic AI Is Security's Next Blind Spot

Agentic AI is already running in production environments across many organizations today. It is executing tasks, consuming data, and taking actions — most likely without meaningful involvement from th...

1 month ago
High nvd

CVE-2026-5029: A remote code execution vulnerability exists in Code Runner MCP Server when run with the --transport http option, which

A remote code execution vulnerability exists in Code Runner MCP Server when run with the --transport http option, which exposes the /mcp JSON-RPC endpoint without authentication on port 3088. An unaut...

8.7
CVSS
1 month ago
Unknown rss_thehackernews

OpenAI Launches Daybreak for AI-Powered Vulnerability Detection and Patch Validation

OpenAI has launched Daybreak, a new cybersecurity initiative that brings together frontier artificial intelligence (AI) model capabilities and Codex Security to help organizations identify and patch v...

Agentic / MCP agentic openai
1 month ago
Medium nvd

CVE-2026-43901: Wireshark MCP is an MCP Server that turns tshark into a structured analysis interface, then layers in optional Wireshark

Wireshark MCP is an MCP Server that turns tshark into a structured analysis interface, then layers in optional Wireshark suite utilities. In 1.1.5 and earlier, wireshark-mcp exposes a wireshark_export...

Agentic / MCP mcp server
6.8
CVSS
1 month ago
Medium github

Duplicate Advisory: OpenClaw: MCP stdio server env could load dangerous startup variables from workspace config

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mj59-h3q9-ghfh. This link is maintained to preserve external references. ### Original Description OpenClaw be...

7.3
CVSS
1 month ago
High github

automagik-genie has a command injection vulnerability

Command injection vulnerability in automagik-genie 2.5.27 MCP Server allows attackers to execute arbitrary commands via the view_task (aka view) in the readTranscriptFromCommit function in dist/mcp/se...

8.1
CVSS
1 month ago
Medium nvd

CVE-2026-45001: OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.appl

OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.apply endpoints that fails to protect operator-trusted settings including sandbox po...

6.0
CVSS
1 month ago
Medium nvd

CVE-2026-44995: OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server configu

OpenClaw before 2026.4.20 contains an improper environment variable validation vulnerability in MCP stdio server configuration that allows attackers to execute arbitrary code. Malicious workspace conf...

5.4
CVSS
1 month ago
High nvd

CVE-2026-30635: Command injection vulnerability in automagik-genie 2.5.27 MCP Server allows attackers to execute arbitrary commands via

Command injection vulnerability in automagik-genie 2.5.27 MCP Server allows attackers to execute arbitrary commands via the view_task (aka view) in the readTranscriptFromCommit function in dist/mcp/se...

8.1
CVSS
1 month ago
Critical github

PraisonAI MCP `tools/call` path-traversal => RCE via Python `.pth` injection

## Summary 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.d...

Prompt Injection Remote Code Execution Agentic / MCP model context protocol prompt injection indirect prompt claude code mcp server anthropic openai claude cursor llm
9.6
CVSS
1 month ago
Low nvd

CVE-2026-44286: FastGPT is an AI Agent building platform. Prior to version 4.14.17, an unauthenticated Server-Side Request Forgery (SSRF

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 privil...

2.3
CVSS
1 month ago
Medium nvd

CVE-2026-44284: FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in M

FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected inte...

SSRF Agentic / MCP mcp server ai agent
6.3
CVSS
1 month ago
High nvd

CVE-2026-42345: FastGPT is an AI Agent building platform. In versions 4.14.11 and prior, FastGPT's isInternalAddress() function in packa

FastGPT is an AI Agent building platform. In versions 4.14.11 and prior, FastGPT's isInternalAddress() function in packages/service/common/system/utils.ts blocks cloud metadata endpoints using a fullU...

7.7
CVSS
1 month ago
Medium nvd

CVE-2026-42344: FastGPT is an AI Agent building platform. In versions 4.14.11 and prior, FastGPT's isInternalAddress() function in packa

FastGPT is an AI Agent building platform. In versions 4.14.11 and prior, FastGPT's isInternalAddress() function in packages/service/common/system/utils.ts is vulnerable to DNS rebinding (TOCTOU — Time...

6.3
CVSS
1 month ago
Medium nvd

CVE-2026-42343: FastGPT is an AI Agent building platform. In versions 4.14.13 and prior, the code-sandbox component suffers from insuffi

FastGPT is an AI Agent building platform. In versions 4.14.13 and prior, the code-sandbox component suffers from insufficient resource isolation and uncontrolled resource consumption. The service reli...

6.3
CVSS
1 month ago
Critical nvd

CVE-2026-42302: FastGPT is an AI Agent building platform. From version 4.14.10 to before version 4.14.13, the agent-sandbox component of

FastGPT is an AI Agent building platform. From version 4.14.10 to before version 4.14.13, the agent-sandbox component of FastGPT is vulnerable to unauthenticated Remote Code Execution (RCE). The start...

9.8
CVSS
1 month ago
Critical github

Cline Kanban Server has a Cross-Origin WebSocket Hijacking Vulnerability

## Summary The `kanban` npm package (used by the `cline` CLI) starts a WebSocket server on `127.0.0.1:3484` with no Origin header validation. Any website a developer visits can silently connect to th...

9.6
CVSS
1 month ago
High nvd

CVE-2026-44694: n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. From

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 r...

7.2
CVSS
1 month ago
Medium nvd

CVE-2026-42282: n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior

n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to version 2.47.13, when n8n-mcp runs in HTTP transport mode, authenticated MCP...

Agentic / MCP mcp server
4.3
CVSS
1 month ago