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

Medium nvd

CVE-2026-44430: The MCP Registry provides MCP clients with a list of MCP servers, like an app store for MCP servers. Prior to 1.7.7, the

The MCP Registry provides MCP clients with a list of MCP servers, like an app store for MCP servers. Prior to 1.7.7, the Registry's HTTP-based namespace verification (POST /v0/auth/http, POST /v0.1/au...

Agentic / MCP mcp server
6.3
CVSS
4 months ago
Medium nvd

CVE-2026-44429: The MCP Registry provides MCP clients with a list of MCP servers, like an app store for MCP servers. Prior to 1.7.7, the

The MCP Registry provides MCP clients with a list of MCP servers, like an app store for MCP servers. Prior to 1.7.7, the public catalogue UI served at GET / (file internal/api/handlers/v0/ui_index.htm...

Agentic / MCP mcp server
5.1
CVSS
4 months ago
High github

python-utcp: Full Process Environment Exposed to CLI Subprocess - Secrets Leakage via Command Injection

## Summary `_prepare_environment()` in `cli_communication_protocol.py` passes a full copy of `os.environ` to every CLI subprocess. When combined with the Command Injection vulnerability (CWE-78) in `...

Remote Code Execution Agentic / MCP anthropic ai agent openai llm
7.7
CVSS
4 months ago
High github

Open WebUI's chat completion API allows tool restrictions to be bypassed

### Summary Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. ### Detai...

Agentic / MCP mcp server llama
7.1
CVSS
4 months ago
Medium github

Home Assistant MCP Server: YAML config backups written under www/ are served unauthenticated at /local/

### Summary When `ENABLE_YAML_CONFIG_EDITING=true`, every `ha_config_set_yaml` call backs up the pre-edit file to `/www/yaml_backups/`, which Home Assistant serves at `/local/` with **no authenticati...

Agentic / MCP mcp server
6.5
CVSS
4 months ago
Low github

dbt MCP Server Transmits All MCP Tool Arguments Including Raw SQL and --vars Credentials to dbt Labs Telemetry by Default Without Redaction

*Discovered through manual source code review. Verified by PoC execution against a local dbt-mcp v1.15.1 installation.* ### Summary `DefaultUsageTracker.emit_tool_called_event()` in `src/dbt_mcp/tra...

Agentic / MCP mcp server
3.1
CVSS
4 months ago
Low github

dbt MCP Server Logs Tool Arguments Including SQL Queries and Credentials in Plaintext Without Redaction When File Logging Is Enabled

*Discovered through manual source code review. Verified by PoC execution against a local dbt-mcp v1.15.1 installation.* ### Summary `DbtMCP.call_tool()` in `src/dbt_mcp/mcp/server.py` logs the compl...

Agentic / MCP mcp server
2.5
CVSS
4 months ago
Medium github

dbt MCP Server has an Argument Injection in dbt CLI Tool Wrappers via node_selection and resource_type Parameters

*Discovered through manual source code review. Verified by PoC execution against a local dbt-mcp v1.15.1 installation.** ## Summary `_run_dbt_command()` in `src/dbt_mcp/dbt_cli/tools.py` constructs...

Agentic / MCP mcp server llm agent llm
6.3
CVSS
4 months ago
Medium nvd

CVE-2026-42572: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.83.39, a

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.83.39, a missing authorization directive on the GET /api/v1/stable/dags/tasks endpoint c...

5.3
CVSS
4 months ago
High nvd

CVE-2026-42559: RMCP is an official Rust SDK for the Model Context Protocol. Prior to version 1.4.0, the rmcp crate's Streamable HTTP se

RMCP is an official Rust SDK for the Model Context Protocol. Prior to version 1.4.0, the rmcp crate's Streamable HTTP server transport (crates/rmcp/src/transport/streamable_http_server/) did not valid...

Agentic / MCP model context protocol mcp server
8.8
CVSS
4 months ago
High github

Flowise has an MCP Security Bypass that Enables RCE

## Summary There are three bypass methods for the security limitations of the Flowise MCP feature, and attackers can execute arbitrary commands by combining these three methods ## Details ### 【Vul...

0.0
CVSS
4 months ago
Medium nvd

CVE-2026-44479: Vercel’s AI Cloud is a unified platform for building modern applications. From 50.16.0 to 52.0.0, hen the Vercel CLI ru

Vercel’s AI Cloud is a unified platform for building modern applications. From 50.16.0 to 52.0.0, hen the Vercel CLI runs in non-interactive mode (--non-interactive or auto-detected AI agent), comman...

5.5
CVSS
4 months ago
Critical github

Obot has an authorization bypass in /mcp-connect/{id} that allows any authenticated user to use any registered MCP server

## Summary If you have the MCP Server ID, you can connect to the MCP server even if you don't have permissions to the server. The MCP gateway endpoint `/mcp-connect/{mcp_id}` does not enforce Access...

Auth Bypass Agentic / MCP claude code mcp server claude
9.6
CVSS
4 months ago
Unknown rss_securityweek

Sweet Security Launches Agentic AI Red Teaming to Counter ‘Mythos Moment’

New “Sweet Attack” platform uses runtime intelligence and continuous agentic red teaming to identify exploitable attack chains human teams may miss. The post Sweet Security Launches Agentic AI Red Tea...

4 months ago
Unknown rss_thehackernews

Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday

Microsoft has unveiled a new multi-model artificial intelligence (AI)-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some c...

Agentic / MCP ai agent agentic
4 months ago
High nvd

CVE-2026-44246: nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nn

nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable...

Agentic / MCP anthropic agentic claude
7.2
CVSS
4 months ago
Low nvd

CVE-2026-44220: ciguard is a static security auditor for CI/CD pipelines. From 0.8.0 to 0.8.1 , the discover_pipeline_files() function i

ciguard is a static security auditor for CI/CD pipelines. From 0.8.0 to 0.8.1 , the discover_pipeline_files() function in src/ciguard/discovery.py walks a directory tree following symlinks, with cycle...

3.2
CVSS
4 months ago
Critical github

Open Source Kubectl MCP Server vulnerable to arbitrary code execution via user interaction with crafted HTML page

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.

9.8
CVSS
4 months ago
Unknown rss_securityweek

Exaforce Raises $125 Million for Agentic SOC Platform

Exaforce has raised a total of $200 million and plans on using the latest investment for product development and international expansion.  The post Exaforce Raises $125 Million for Agentic SOC Platfor...

4 months ago
High nvd

CVE-2026-43993: JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, the WAVS bridge's computeDataVerify

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, the WAVS bridge's computeDataVerify called fetch() on agent-supplied URLs without validating scheme, port, or resol...

8.2
CVSS
4 months ago
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
4 months 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
4 months 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
4 months 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
4 months 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
4 months ago