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

Medium github

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

## Affected Packages / Versions - Package: `openclaw` (npm) - Affected versions: `< 2026.4.20` - Patched version: `2026.4.20` ## Impact Workspace MCP stdio configuration could pass dangerous proces...

Agentic / MCP mcp server
0.0
CVSS
1 month ago
Medium osv

LiteLLM: Authenticated command execution via MCP stdio test endpoints

### Impact Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request b...

4.0
CVSS
1 month ago
Unknown rss_thehackernews

Bridging the AI Agent Authority Gap: Continuous Observability as the Decision Engine

The AI Agent Authority Gap - From Ungoverned to Delegation As discussed in our previous article, AI agents are exposing a structural gap in enterprise security, but the problem is often framed too nar...

1 month ago
Unknown rss_securityweek

Copperhelm Raises $7 Million for Agentic Cloud Security Platform

The Israel-based company, which just emerged from stealth mode, was founded by cloud and security experts from RSA, McAfee, and Unity. The post Copperhelm Raises $7 Million for Agentic Cloud Security...

1 month ago
High nvd

CVE-2026-41349: OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execu

OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to b...

Agentic / MCP llm agent agentic llm
8.7
CVSS
1 month ago
Critical nvd

CVE-2026-41679: Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Prior to version 202

Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Prior to version 2026.416.0, an unauthenticated attacker can achieve full remote code execution on a...

10.0
CVSS
1 month ago
High nvd

CVE-2026-41208: Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Versions of @papercl

Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Versions of @paperclipai/server prior to 2026.416.0 contain a privilege escalation vulnerability tha...

8.8
CVSS
1 month ago
Unknown rss_thehackernews

Toxic Combinations: When Cross-App Permissions Stack into Risk

On January 31, 2026, researchers disclosed that Moltbook, a social network built for AI agents, had left its database wide open, exposing 35,000 email addresses and 1.5 million agent API tokens across...

Agentic / MCP ai agent openai
1 month ago
Critical github

Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

## Abstract Trend Micro's Zero Day Initiative has identified a vulnerability affecting FlowiseAI Flowise. ## Vulnerability Details - **Version tested:** 3.0.13 - **Installer file:** https://github....

Prompt Injection Remote Code Execution Agentic / MCP large language model prompt injection ai agent llm
9.8
CVSS
2 months ago
Medium nvd

CVE-2026-40608: Next AI Draw.io is a next.js web application that integrates AI capabilities with draw.io diagrams. Prior to 0.4.15, the

Next AI Draw.io is a next.js web application that integrates AI capabilities with draw.io diagrams. Prior to 0.4.15, the embedded HTTP sidecar contains three POST handlers (/api/state, /api/restore, a...

Agentic / MCP mcp server
6.2
CVSS
2 months ago
Unknown rss_thehackernews

Google Patches Antigravity IDE Flaw Enabling Prompt Injection Code Execution

Cybersecurity researchers have discovered a vulnerability in Google's agentic integrated development environment (IDE), Antigravity, that could be exploited to achieve code execution. The flaw, since...

Prompt Injection Agentic / MCP prompt injection agentic
2 months ago
Medium github

Apache Doris MCP Server vulnerable to SQL Injection via improper query context neutralization

Apache Doris MCP Server versions prior to 0.6.1 are affected by an improper neutralization flaw in query context handling that may allow execution of unintended SQL statements and bypass of intended q...

Agentic / MCP mcp server
5.3
CVSS
2 months ago
Unknown rss_thehackernews

Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture that could pave the way for remote code execution and have a cascading effe...

2 months ago
Low github

Langflow vulnerable to injection

A vulnerability was detected in langflow-ai langflow up to 1.8.3. The impacted element is the function get_client_ip/install_mcp_config of the file src/backend/base/langflow/api/v1/mcp_projects.py of...

Agentic / MCP model context protocol langflow
6.3
CVSS
2 months ago
Unknown rss_thehackernews

[Webinar] Eliminate Ghost Identities Before They Expose Your Enterprise Data

In 2024, compromised service accounts and forgotten API keys were behind 68% of cloud breaches. Not phishing. Not weak passwords. Unmanaged non-human identities that nobody was watching. For every emp...

2 months ago
Critical github

Flowise: Airtable_Agent Code Injection Remote Code Execution Vulnerability

ZDI-CAN-29412: FlowiseAI Flowise Airtable_Agent Code Injection Remote Code Execution Vulnerability Trend Micro's Zero Day Initiative has identified a vulnerability affecting the following products: F...

Prompt Injection Remote Code Execution Agentic / MCP large language model prompt injection langchain ai agent ollama llama llm
9.8
CVSS
2 months ago
Critical github

PraisonAI has an incomplete fix for CVE-2026-34935 - OS Command Injection

### Summary The fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to `parse_mcp_command()`, allowing arbitrary executables like `bash`, `python`, or `/b...

9.8
CVSS
2 months ago
Low github

Neo4j Labs MCP Servers: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures

### Summary The `read_only` mode in `mcp-neo4j-cypher` versions prior to 0.6.0 can be bypassed using `CALL` procedures. ### Details #### Impact The enforcing of `read_only` mode in vulnerable versio...

0.0
CVSS
2 months ago
High github

Flowise: resetPassword Authentication Bypass Vulnerability

ZDI-CAN-28762: Flowise AccountService resetPassword Authentication Bypass Vulnerability -- ABSTRACT ------------------------------------- Trend Micro's Zero Day Initiative has identified a vulnerabi...

Auth Bypass Agentic / MCP large language model ai agent llm
9.8
CVSS
2 months ago
High github

Flowise: Parameter Override Bypass Remote Command Execution

### Summary Flowise is vulnerable to a critical unauthenticated remote command execution (RCE) vulnerability. It can be exploited via a parameter override bypass using the `FILE-STORAGE::` keyword co...

7.7
CVSS
2 months ago
Unknown rss_thehackernews

Deterministic + Agentic AI: The Architecture Exposure Validation Requires

Few technologies have moved from experimentation to boardroom mandate as quickly as AI. Across industries, leadership teams have embraced its broader potential, and boards, investors, and executives a...

2 months ago
Critical github

excel-mcp-server has a Path Traversal issue

## Summary A path traversal vulnerability exists in [`excel-mcp-server`](https://github.com/haris-musa/excel-mcp-server) versions up to and including `0.1.7`. When running in SSE or Streamable-HTTP t...

9.4
CVSS
2 months ago
Medium github

PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

## Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves `execute_command` for any command (e.g., `ls -la...

Prompt Injection Agentic / MCP prompt injection llm agent openai llm
5.5
CVSS
2 months ago
Critical github

nginx-ui's Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

### Summary The nginx-ui MCP (Model Context Protocol) integration exposes two HTTP endpoints: `/mcp` and `/mcp_message`. While `/mcp` requires both IP whitelisting and authentication (`AuthRequired()`...

Agentic / MCP model context protocol
9.8
CVSS
2 months ago
Critical github

Langflow has Authenticated Code Execution in Agentic Assistant Validation

## Description ### 1. Summary The Agentic Assistant feature in Langflow executes LLM-generated Python code during its **validation** phase. Although this phase appears intended to validate generated...

Agentic / MCP langflow agentic llm
0.0
CVSS
2 months ago