CVE-2026-9680 MCP Server Exposure via Insecure Default Binding on alibabacloud-rds-openapi-mcp-server

Improper exposure of the MCP server in alibabacloud-rds-openapi-mcp-server allows remote attackers to invoke exposed MCP tools via network access to an MCP endpoint listening on all network interfaces by default...

PYSEC-2026-3479 LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

Impact LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token. The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key...

GHSA-P39J-X9H5-Q66M OpenClaw: Embedded runner policy could be confused by provider aliases

Summary Embedded runner policy could be confused by provider aliases. In affected versions, a request using provider aliases could compare policy against an alias instead of the canonical provider identity. This advisory is scoped to the named feature and configuration. It does not change...

CVE-2026-58168 DeepTutor < 1.4.10 - Insecure Default Grants Unrestricted MCP Tool Access to Non-Admin Users

DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowedmcptools function returning None instead of a denied result when mcptools is omitted from a user's grant in...

CVE-2026-58168

Vulnerability overview: DeepTutor prior to v1.4.10 contains an authorization bypass in which the allowed_mcp_tools function returns None instead of denying access when mcp_tools is omitted from a user’s grant in deeptutor/multi_user/tool_access.py. This enables low-privilege users, including thos...

CVE-2026-58168 DeepTutor < 1.4.10 - Insecure Default Grants Unrestricted MCP Tool Access to Non-Admin Users

DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowedmcptools function returning None instead of a denied result when mcptools is omitted from a user's grant in...

EUVD-2026-40375

DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowedmcptools function returning None instead of a denied result when mcptools is omitted from a user's grant in...

PYSEC-2026-468 PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

GHSA-X975-RGX4-5FH4 appium-mcp: Unescaped Locator Data XSS in MCP-UI Resource (createLocatorGeneratorUI)

Unescaped Locator Data XSS in MCP-UI Resource createLocatorGeneratorUI Summary appium-mcp's createLocatorGeneratorUI function interpolates attacker-controlled element attributes — text, content-desc, resource-id, and locator selector values — directly into an HTML template literal without any HTM...

Missing Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

CVE-2026-53809

OpenClaw before 2026.4.25 contains a policy bypass vulnerability in embedded runner policy that allows requests using provider aliases to compare against aliases instead of canonical provider identities. Attackers can exploit this confusion to select bundled tool access outside intended provider...

CVE-2026-53809 OpenClaw < 2026.4.25 - Provider Alias Confusion in Embedded Runner Policy

OpenClaw before 2026.4.25 contains a policy bypass vulnerability in embedded runner policy that allows requests using provider aliases to compare against aliases instead of canonical provider identities. Attackers can exploit this confusion to select bundled tool access outside intended provider...

CVE-2026-53809 OpenClaw < 2026.4.25 - Provider Alias Confusion in Embedded Runner Policy

OpenClaw before 2026.4.25 contains a policy bypass vulnerability in embedded runner policy that allows requests using provider aliases to compare against aliases instead of canonical provider identities. Attackers can exploit this confusion to select bundled tool access outside intended provider...

State of Agentic AI Security and Governance

An OWASP white paper analyzing the security, governance, and risk management considerations surrounding agentic AI systems, including autonomous decision-making, tool access, prompt injection, data protection, and organizational oversight. This is version 2.01...

Linux Distros Unpatched Vulnerability : CVE-2026-44301

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node- based asset pipelines PostCSS, Babel, TailwindCSS, Hugo...

CVE-2026-44301 Hugo: Node tool execution allows file system access outside the project directory

Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node-based asset pipelines PostCSS, Babel, TailwindCSS, Hugo invoked the configured Node tools without restrictions on file system access. As a result, executing hugo against an untrusted site could...

CVE-2026-45001 OpenClaw < 2026.4.20 - Gateway Config Mutation Guard Bypass via Agent Tool Access

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 policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

CVE-2026-45001 OpenClaw < 2026.4.20 - Gateway Config Mutation Guard Bypass via Agent Tool Access

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 policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

PT-2026-29829

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.5.97 Description An authentication bypass exists in the multi-agent teams system where the validate token function within OAuthManager returns True for any token not found in its internal store, which is empty by...