# praisonai (npm) vulnerabilities

Source: https://junglewise.ai/threats/technologies/npm-praisonai  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour.  
Data: https://junglewise.ai/threats/technologies/npm-praisonai.json  
License: CC BY 4.0 with a link back

Junglewise Threat Intelligence has tracked 9 vulnerabilities in praisonai (npm): 0 in the last 7 days and 7 in the last 90 days, 2 of them critical and 0 exploited in the wild. The most recent, CVE-2026-57141, was published on 15 September 2026. Nothing in the last four weeks, down from 7 vulnerabilities in the four before. 0 critical against 2.

## Counts

- Last 7 days: 0
- Last 30 days: 0
- Last 90 days: 7
- All time: 9 (2 critical, 0 exploited in the wild)

## About praisonai (npm)

Node.js library for building AI agent systems and orchestrating multi-agent workflows.

## Latest praisonai (npm) vulnerabilities

- [CVE-2026-57141: PraisonAI codeMode tool remote code execution via sandbox escape](https://junglewise.ai/threats/cve-2026-57141-praisonai-codemode-tool-remote-code-execution-via-sandbox-escape) (critical, CVSS 9.8, published 15 Sep 2026)
- [CVE-2026-57138: npm PraisonAI codeMode sandbox escape via Function constructor](https://junglewise.ai/threats/cve-2026-57138-npm-praisonai-codemode-sandbox-escape-via-function-constructor) (critical, CVSS 9.9, published 15 Sep 2026)
- [CVE-2026-57137: PraisonAI AgentLoop approval bypass via post-execution callback](https://junglewise.ai/threats/cve-2026-57137-praisonai-agentloop-approval-bypass-via-post-execution-callback) (high, CVSS 8.8, published 15 Sep 2026)
- [CVE-2026-57136: PraisonAI SandboxExecutor command allowlist bypass via shell chaining](https://junglewise.ai/threats/cve-2026-57136-praisonai-sandboxexecutor-command-allowlist-bypass-via-shell) (high, CVSS 8.8, published 15 Sep 2026)
- [CVE-2026-57135: PraisonAI SandboxExecutor network isolation bypass via non-proxy-aware clients](https://junglewise.ai/threats/cve-2026-57135-praisonai-sandboxexecutor-network-isolation-bypass-via-non-proxy) (high, CVSS 7.6, published 15 Sep 2026)
- [CVE-2026-57134: npm PraisonAI MCPSecurity auth bypass in Basic/OAuth validation](https://junglewise.ai/threats/cve-2026-57134-npm-praisonai-mcpsecurity-auth-bypass-in-basic-oauth-validation) (high, CVSS 8.2, published 15 Sep 2026)
- [CVE-2026-57133: PraisonAI shell command allowlist bypass via shell chaining](https://junglewise.ai/threats/cve-2026-57133-praisonai-shell-command-allowlist-bypass-via-shell-chaining) (high, CVSS 8.8, published 15 Sep 2026)
- [Duplicate Advisory: PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent…](https://junglewise.ai/threats/duplicate-advisory-praisonai-agentos-defaults-to-network-exposed-no-8ca29195) (high, CVSS 8.6, published 11 Jul 2026)
- [CVE-2026-61426: MervinPraison PraisonAI missing authentication in AgentOS API](https://junglewise.ai/threats/cve-2026-61426-mervinpraison-praisonai-missing-authentication-in-agentos-api) (high, CVSS 8.6, published 11 Jul 2026)

## Most severe praisonai (npm) vulnerabilities

- [CVE-2026-57138: npm PraisonAI codeMode sandbox escape via Function constructor](https://junglewise.ai/threats/cve-2026-57138-npm-praisonai-codemode-sandbox-escape-via-function-constructor) (critical, CVSS 9.9, published 15 Sep 2026)
- [CVE-2026-57141: PraisonAI codeMode tool remote code execution via sandbox escape](https://junglewise.ai/threats/cve-2026-57141-praisonai-codemode-tool-remote-code-execution-via-sandbox-escape) (critical, CVSS 9.8, published 15 Sep 2026)
- [CVE-2026-57133: PraisonAI shell command allowlist bypass via shell chaining](https://junglewise.ai/threats/cve-2026-57133-praisonai-shell-command-allowlist-bypass-via-shell-chaining) (high, CVSS 8.8, published 15 Sep 2026)
- [CVE-2026-57136: PraisonAI SandboxExecutor command allowlist bypass via shell chaining](https://junglewise.ai/threats/cve-2026-57136-praisonai-sandboxexecutor-command-allowlist-bypass-via-shell) (high, CVSS 8.8, published 15 Sep 2026)
- [CVE-2026-57137: PraisonAI AgentLoop approval bypass via post-execution callback](https://junglewise.ai/threats/cve-2026-57137-praisonai-agentloop-approval-bypass-via-post-execution-callback) (high, CVSS 8.8, published 15 Sep 2026)
- [CVE-2026-61426: MervinPraison PraisonAI missing authentication in AgentOS API](https://junglewise.ai/threats/cve-2026-61426-mervinpraison-praisonai-missing-authentication-in-agentos-api) (high, CVSS 8.6, published 11 Jul 2026)
- [Duplicate Advisory: PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent…](https://junglewise.ai/threats/duplicate-advisory-praisonai-agentos-defaults-to-network-exposed-no-8ca29195) (high, CVSS 8.6, published 11 Jul 2026)
- [CVE-2026-57134: npm PraisonAI MCPSecurity auth bypass in Basic/OAuth validation](https://junglewise.ai/threats/cve-2026-57134-npm-praisonai-mcpsecurity-auth-bypass-in-basic-oauth-validation) (high, CVSS 8.2, published 15 Sep 2026)
- [CVE-2026-57135: PraisonAI SandboxExecutor network isolation bypass via non-proxy-aware clients](https://junglewise.ai/threats/cve-2026-57135-praisonai-sandboxexecutor-network-isolation-bypass-via-non-proxy) (high, CVSS 7.6, published 15 Sep 2026)

## Vulnerabilities per week

Nothing in the last four weeks, down from 7 vulnerabilities in the four before. 0 critical against 2.

| Week of | Vulns | Critical | Exploited |
| --- | --- | --- | --- |
| 17 Aug 2026 | 0 | 0 | 0 |
| 24 Aug 2026 | 0 | 0 | 0 |
| 31 Aug 2026 | 0 | 0 | 0 |
| 7 Sep 2026 | 0 | 0 | 0 |
| 14 Sep 2026 | 7 | 2 | 0 |
| 21 Sep 2026 | 0 | 0 | 0 |
| 28 Sep 2026 | 0 | 0 | 0 |
| 5 Oct 2026 | 0 | 0 | 0 |
| 12 Oct 2026 | 0 | 0 | 0 |
| 19 Oct 2026 | 0 | 0 | 0 |
| 26 Oct 2026 | 0 | 0 | 0 |
| 2 Nov 2026 | 0 | 0 | 0 |
| 9 Nov 2026 | 0 | 0 | 0 |

## Other npm technologies

- [openclaw (npm)](https://junglewise.ai/threats/technologies/npm-openclaw): 214 vulnerabilities
- [flowise (npm)](https://junglewise.ai/threats/technologies/flowise): 133 vulnerabilities
- [parse-server (npm)](https://junglewise.ai/threats/technologies/parse-server): 117 vulnerabilities
- [vm2 (npm)](https://junglewise.ai/threats/technologies/vm2): 111 vulnerabilities
- [electron (npm)](https://junglewise.ai/threats/technologies/electron): 77 vulnerabilities
- [ghost (npm)](https://junglewise.ai/threats/technologies/ghost): 74 vulnerabilities
- [n8n (npm)](https://junglewise.ai/threats/technologies/npm-n8n): 64 vulnerabilities
- [hono (npm)](https://junglewise.ai/threats/technologies/hono): 62 vulnerabilities
- [directus (npm)](https://junglewise.ai/threats/technologies/directus): 61 vulnerabilities
- [nocodb (npm)](https://junglewise.ai/threats/technologies/nocodb): 54 vulnerabilities
- [undici (npm)](https://junglewise.ai/threats/technologies/undici): 53 vulnerabilities
- [@budibase/server (npm)](https://junglewise.ai/threats/technologies/budibase-server): 42 vulnerabilities

## Sources

NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "praisonai (npm) vulnerabilities", https://junglewise.ai/threats/technologies/npm-praisonai, 13 November 2026.