CVE-2026-62316

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, ufo/client/mcp/httpservers/linuxmcpserver.py binds a FastMCP streamable HTTP server to localhost:8010 but does not validate the Host, Origin, or Sec-Fetch-Site headers. An...

CVE-2026-62675 Omnigent: Uploaded Agent Bundle Allows Authenticated Runner RCE via Python Callable Tools

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, multipart POST /v1/sessions accepts an authenticated user's agent bundle and omnigent/server/bundles.py validateagentbundle does not reject a tools..callable dotted Python path...

CVE-2026-62674

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

Incorrect Authorization

Overview org.springframework.ai:spring-ai-model is a Core model interfaces and classes for Spring AI Affected versions of this package are vulnerable to Incorrect Authorization through the DefaultToolCallingManager in...

prismsec

PrismSec 🔷 Secure, modular MCP server for pentesting tools...

CVE-2026-61539: Improper Neutralization of Directives in Dynamically Evaluated Code

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

Oracle WebCenter Portal (August 2026 CSPU)

The 12.2.1.4.0 and 14.1.2.0.0 versions of WebCenter Portal installed on the remote host are affected by multiple vulnerabilities as referenced in the August 2026 CSPU advisory. - Vulnerability in the Oracle WebCenter Portal product of Oracle Fusion Middleware component: Composer. Supported versio...

AZL-97512 CVE-2026-72854 affecting package lttng-tools 2.13.11-1

msgpackunpackerexpandbuffer in src/unpack.c, reached through the public msgpackunpackerreservebuffer API, computes its new buffer size using an unchecked sizet addition of the requested size and the amount already used. The doubling loop guards its own multiplication against overflow, but the...

Moderate: Red Hat Security Advisory: Red Hat AI Inference Model Optimization Tools 3.4.4 (cuda)

Red Hat AI Inference Model Optimization Tools 3.4.4 cuda is now available. Red Hat AI Inference Model Optimization Tools...

Awesome-Bug-Bounty-Tools-Contents

Awesome-Bug-Bounty-Tools-Contents A comprehensive Bug Bounty a...

AEGIS: Preventing Cross-Domain Resource Abuse in MCP

The Model Context Protocol MCP is an open source JSON-RPC protocol that standardizes how large language models LLMs interact with external systems through programmatic functions known as tools. Attackers or malicious agents can exploit certain modalities of these MCP tools to degrade the overall...

GHSA-2XHG-73J7-RRGX Contentful MCP Server: export_space/import_space tools pass LLM-controlled `host`/`proxy` args to CMA client, redirecting server PAT to attacker-controlled endpoint

Summary exportspace and importspace tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host — t...

Contentful MCP Server: export_space/import_space tools pass LLM-controlled `host`/`proxy` args to CMA client, redirecting server PAT to attacker-controlled endpoint

Summary exportspace and importspace tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host — t...

@contentful/mcp-server (>=1.7.0-dev-20251016T1739-07b05ef.0, <=1.7.18), @iflow-mcp/contentful-contentful-mcp-server (>=1.7.7, <=1.7.8) potentially affected by CVE-2026-53957 via @contentful/mcp-tools (>=0.1.0, <=0.4.4)

@contentful/mcp-tools NPM version =0.1.0, =1.7.0-dev-20251016T1739-07b05ef.0, =1.7.7, =1.7.8 Source cves: CVE-2026-53957 Source advisory: OSV:GHSA-2XHG-73J7-RRGX...

GHSA-J4R7-8PH4-43G3 faf-mcp has an arbitrary local file read/write via unconfined `path` argument in FAF tools

Summary faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read/write without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be made to...

PYSEC-2026-3685 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 kubectlget, kubectldescribe, kubectldelete that allows attackers to bypass the assertNoDangerousFlags security check by supplying resourceType and name parameters with leading dashes. Attackers can...

Exploit for CVE-2026-47858

CVE-2026-47858 Replay Experiment Record Vulnerability: Sp...

CyberStrikeAI v1.7.15

CyberStrikeAI 中文 | English The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next. CyberStrikeAI connects planning, execution, human oversight, evidence, and replay in one auditable...

PT-2026-83509

Summary Several grok-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...

PT-2026-80207

Summary export space and import space tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host —...