VulnWatch VulnWatch
← Back to dashboard
#

Agentic / MCP

653 entries

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

Subscribe to this tag's RSS feed

High github

MKP: Unbounded Pod Log Read via Attacker-Controlled `limitBytes`/`tailLines` Causes Memory Exhaustion

## Unbounded Pod Log Read via Attacker-Controlled `limitBytes`/`tailLines` Causes Memory Exhaustion ### Summary The MKP (Model Context Protocol for Kubernetes) server exposes a `get_resource` MCP to...

Agentic / MCP model context protocol
7.5
CVSS
2 months ago
High nvd

CVE-2026-58500: MCP Appium is an MCP server that provides AI assistants with tools to automate mobile app testing on Android and iOS. In

MCP Appium is an MCP server that provides AI assistants with tools to automate mobile app testing on Android and iOS. In versions prior to 1.85.10, the createLocatorGeneratorUI function interpolates a...

Agentic / MCP mcp server
8.2
CVSS
2 months 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
2 months ago
Unknown rss_thehackernews

New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email

Give an AI assistant a memory and access to your inbox, and you hand an attacker a way to rewrite what it thinks it knows about you. A single email can trick that agent into saving a false "fact" abou...

2 months ago
Unknown rss_thehackernews

Thinking Fast and Slow in the SOC: The Case for Combining Autonomous AI with Analyst Copilots

A few days ago, I was sitting with the CISO of a Fortune 50 company, walking through how his security team was thinking about AI agents in the SOC. Smart team. Serious program. They had already connec...

Agentic / MCP ai agent copilot claude
2 months ago
Unknown rss_bleepingcomputer

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open im...

Prompt Injection Agentic / MCP prompt injection ai agent
2 months ago
Critical github

mcp-server-kubernetes argument injection can expose Kubernetes cluster credentials

MCP Server Kubernetes before 3.9.0 contains an argument injection vulnerability in structured tools (kubectl_get, kubectl_describe, kubectl_delete) that allows attackers to bypass the assertNoDangerou...

Agentic / MCP mcp server
9.8
CVSS
2 months ago
High github

mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment

### Summary `confluence_upload_attachment` passes `file_path` directly to `open(file_path, "rb")` with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injectio...

Prompt Injection Agentic / MCP prompt injection ai agent qwen
7.7
CVSS
2 months ago
Unknown rss_bleepingcomputer

The Replicant in Your Directory: AI Agents and the Identity Security Gap

AI agents are accelerating the growth of non-human identities, making it harder for organizations to understand what exists, who owns it, and what it can access. Netwrix explains why stronger visibili...

2 months ago
High nvd

CVE-2026-50181: Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's `Rea

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's `ReadFileTool` and `WriteFileTool` appear to treat `curr_dir` as the intended workin...

Agentic / MCP llm agent llm
7.1
CVSS
2 months ago
Medium nvd

CVE-2026-55605: DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.8.0, the self-hos

DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.8.0, the self-hosted HTTP transport of `@arikusi/deepseek-mcp-server` exposes `POST /mcp` without...

Agentic / MCP mcp server deepseek
5.3
CVSS
2 months ago
High nvd

CVE-2026-55604: DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.7.0, the process-

DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.7.0, the process-global `SessionStore` accepts caller-supplied `session_id` values without bindin...

Agentic / MCP mcp server deepseek
8.6
CVSS
2 months ago
High nvd

CVE-2026-59207: n8n is an open source workflow automation platform. Prior to 2.27.4 and 2.28.1, the AI Agents feature did not enforce th

n8n is an open source workflow automation platform. Prior to 2.27.4 and 2.28.1, the AI Agents feature did not enforce the Allowed HTTP Request Domains restriction configured on credentials when an MCP...

7.1
CVSS
2 months ago
Unknown rss_securityweek

UK Government Rolls Out Agentic AI Defense Plan Alongside Industry Pledge

Two announcements on July 7, 2026, demonstrate the government’s determination to improve the level of cybersecurity within the UK. The post UK Government Rolls Out Agentic AI Defense Plan Alongside In...

2 months ago
Unknown rss_thehackernews

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by...

Agentic / MCP claude code anthropic ai agent openai claude
2 months ago
Unknown rss_securityweek

Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection

Researchers show how attackers can use a crafted public GitHub Issue to trick AI-powered workflows into exposing data from private repositories without authentication. The post Critical Vulnerability...

Prompt Injection Agentic / MCP prompt injection agentic
2 months ago
Unknown rss_bleepingcomputer

CISA orders feds to prioritize patching Langflow auth bypass flaw

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) gave federal agencies until Friday to patch an actively exploited vulnerability in the Langflow visual framework for building AI agents...

2 months ago
High github

@better-auth/oauth-provider's OAuth authorization-code grant allows concurrent redemption when two token requests race the find-then-delete primitive

### Am I affected? Users are affected if all of the following are true: - Their project depends on `@better-auth/oauth-provider` at a version `>= 1.6.0, < 1.6.11`, or uses the embedded plugin in `be...

8.1
CVSS
2 months ago
High github

Better Auth has stored XSS in the auth-server origin via javascript: redirect_uri in oidc-provider and mcp

### Am I affected? Check each condition. Users are affected when all of the first three hold. - Their application enables the `oidc-provider` plugin or the `mcp` plugin from `better-auth/plugins`. T...

Agentic / MCP mcp server
7.7
CVSS
2 months ago
Medium github

@aborruso/ckan-mcp-server: SSRF via base_url allows access to internal networks (Potential fix bypass of CVE-2026-33060)

### Summary A known vulnerability CVE-2026-33060 indicated tools including ckan_package_search and sparql_query that accept a base_url parameter had the risk of making HTTP requests to arbitrary endpo...

5.7
CVSS
2 months ago
Unknown rss_thehackernews

Public GitHub Issue Could Trick GitHub Agentic Workflows Into Leaking Private Repo Data

A public issue can trick GitHub Agentic Workflows into leaking the contents of an organization's private repositories, researchers at Noma Security have shown. The attacker needs only to open a norma...

2 months ago
Unknown rss_thehackernews

⚡ Weekly Recap: Proxy Botnets, Browser Ransomware, AI Agent Tricks, Fake PoC Malware and More

A streaming box should not need a threat model. Neither should a username field, a demo repo, a reset flow, or a browser permission prompt. That is the irritating part this week: the risky pieces were...

2 months ago
Unknown rss_securityweek

Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments

Researchers uncovered two campaigns embedding indirect prompt injections in malicious websites to exploit autonomous AI agents browsing the web. The post Prompt Injection Attacks Trick AI Agents Into...

Prompt Injection Agentic / MCP prompt injection indirect prompt ai agent
2 months ago
High nvd

CVE-2026-44934: A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM

A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM response text with potential sensitive data into logfiles, allowing local attac...

7.0
CVSS
2 months ago
Unknown rss_thehackernews

SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing

Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong...

2 months ago