CVE detail
CVE-2026-40159
PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP (Model Context Protocol) integration allows spawning background servers via stdio using user-supplied command strings (e.g., MCP("npx -y @smithery/cli ...")). These commands are executed through Python’s subprocess module. By default, the implementation forwards the entire parent process environment to the spawned subprocess. As a result, any MCP command executed in this manner inherits all environment variables from the host process, including sensitive data such as API keys, authentication tokens, and database credentials. This behavior introduces a security risk when untrusted or third-party commands are used. In common scenarios where MCP tools are invoked via package runners such as npx -y, arbitrary code from external or potentially compromised packages may execute with access to these inherited environment variables. This creates a risk of unintended credential exposure and enables potential supply chain attacks through silent exfiltration of secrets. This vulnerability is fixed in 4.5.128.
Buzz score
Why this CVE is surfacing
This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.
Buzz score components · mention 6.9 · diversity 5.0 · KEV 0.0 · OTX 0.0 · PoC 0.0
Why it matters now
Mention timeline
- Total mentions
- 0
- within the 30d window
- Peak daily
- 0
- highest bucket
Evidence
Source links by recency
1 source links · newest first
No excerpt available.
Exploitgithub.comApr 10, 2026, 5:17 PM
Exploit code
Public exploit repository references
Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.
0 repository references · best confidence N/A · max 0 stars
Related records
Similar CVEs
6 related CVEs with shared weakness or product evidence
- CVE-2024-39314CVSS 4.7 · Medium
toy-blog is a headless content management system implementation. Starting in version 0.4.3 and prior to version 0.5.0, the administrative password was leaked through the command l…
- CVE-2020-36771CVSS 7.8 · High
CloudLinux CageFS 7.1.1-1 or below passes the authentication token as a command line argument. In some configurations this allows local users to view the authentication token via…
- CVE-2021-32638CVSS 4.4 · Medium
Github's CodeQL action is provided to run CodeQL-based code scanning on non-GitHub CI/CD systems and requires a GitHub access token to connect to a GitHub repository. The runner a…
- CVE-2020-1753CVSS 5.0 · Medium
A security flaw was found in Ansible Engine, all Ansible 2.7.x versions prior to 2.7.17, all Ansible 2.8.x versions prior to 2.8.11 and all Ansible 2.9.x versions prior to 2.9.7,…
- CVE-2019-3869CVSS 7.2 · High
When running Tower before 3.4.3 on OpenShift or Kubernetes, application credentials are exposed to playbook job runs via environment variables. A malicious user with the ability t…
- CVE-2026-40151CVSS 5.3 · Medium
PraisonAI is a multi-agent teams system. Prior to 4.5.128, the AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 ch…