Technology · Praison
PraisonAI vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 19 vulnerabilities in PraisonAI: 0 in the last 7 days and 1 in the last 90 days, 8 of them critical and 0 exploited in the wild. The most recent, CVE-2026-47397, was published on 21 July 2026.
- Last 7 days
- 0
- Last 90 days
- 1
- Critical, all time
- 8
- Exploited in the wild
- 0
About PraisonAI
An AI agents framework that combines AutoGen, CrewAI, and other multi-agent systems into a low-code solution.
Latest PraisonAI vulnerabilities
- CVE-2026-47397: PraisonAI arbitrary file write via path traversal in write_file toolhighCVSS 4EPSS 0.5%
- PraisonAI tool approval cache bypass in shell command executionmediumCVSS 5.5
- CVE-2026-56075: PraisonAI arbitrary shell command execution in UI moduleshighCVSS 8.8EPSS 0.7%
- CVE-2026-44336: MervinPraison PraisonAI path traversal and RCE in MCP servercriticalCVSS 9.6EPSS 0.7%
- CVE-2026-40159: MervinPraison PraisonAI sensitive information exposure in MCP integrationmediumCVSS 5.5EPSS 0.2%
- CVE-2026-40158: PraisonAI Python sandbox escape via type.__getattribute__highCVSS 8.6EPSS 0.2%
- CVE-2026-40157: MervinPraison PraisonAI path traversal in recipe CLIcriticalCVSS 8.8EPSS 0.5%
- CVE-2026-40156: PraisonAI arbitrary code execution via automatic tools.py loadinghighCVSS 7.8EPSS 0.2%
- CVE-2026-39891: MervinPraison PraisonAI template injection in agent toolshighCVSS 8.8EPSS 0.6%
- CVE-2026-39890: MervinPraison PraisonAI RCE via YAML deserialization in AgentServicecriticalCVSS 9.8EPSS 0.8%
- CVE-2026-39889: MervinPraison PraisonAI authentication bypass in A2U event stream serverhighCVSS 7.5EPSS 0.5%
- CVE-2026-39888: PraisonAI sandbox escape via frame traversal in execute_codecriticalCVSS 9.9EPSS 0.6%
- CVE-2026-34955: MervinPraison PraisonAI sandbox escape in SubprocessSandboxhighCVSS 8.8EPSS 0.4%
- CVE-2026-34953: MervinPraison PraisonAI authentication bypass in OAuthManagercriticalCVSS 9.1EPSS 0.4%
- CVE-2026-34952: MervinPraison PraisonAI missing authentication in WebSocket GatewaycriticalCVSS 9.1EPSS 0.5%
- CVE-2026-34939: MervinPraison PraisonAI ReDoS in MCPToolIndex.search_toolsmediumCVSS 6.5EPSS 0.4%
- CVE-2026-34936: MervinPraison PraisonAI SSRF in passthrough functionshighCVSS 7.7EPSS 0.4%
- CVE-2026-34935: MervinPraison PraisonAI OS command injection in MCPHandlercriticalCVSS 9.8EPSS 1.0%
- CVE-2026-34934: MervinPraison PraisonAI SQL injection in get_all_user_threadscriticalCVSS 9.8EPSS 0.6%
Most severe PraisonAI vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-39888: PraisonAI sandbox escape via frame traversal in execute_codecriticalCVSS 9.9EPSS 0.6%
- CVE-2026-34935: MervinPraison PraisonAI OS command injection in MCPHandlercriticalCVSS 9.8EPSS 1.0%
- CVE-2026-39890: MervinPraison PraisonAI RCE via YAML deserialization in AgentServicecriticalCVSS 9.8EPSS 0.8%
- CVE-2026-34934: MervinPraison PraisonAI SQL injection in get_all_user_threadscriticalCVSS 9.8EPSS 0.6%
- CVE-2026-44336: MervinPraison PraisonAI path traversal and RCE in MCP servercriticalCVSS 9.6EPSS 0.7%
- CVE-2026-34952: MervinPraison PraisonAI missing authentication in WebSocket GatewaycriticalCVSS 9.1EPSS 0.5%
- CVE-2026-34953: MervinPraison PraisonAI authentication bypass in OAuthManagercriticalCVSS 9.1EPSS 0.4%
- CVE-2026-40157: MervinPraison PraisonAI path traversal in recipe CLIcriticalCVSS 8.8EPSS 0.5%
- CVE-2026-56075: PraisonAI arbitrary shell command execution in UI moduleshighCVSS 8.8EPSS 0.7%
- CVE-2026-39891: MervinPraison PraisonAI template injection in agent toolshighCVSS 8.8EPSS 0.6%
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 29 Jun 2026 | 0 | 0 | |
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 0 | 0 | |
| 20 Jul 2026 | 1 | 0 | |
| 27 Jul 2026 | 0 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/praisonai.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "PraisonAI vulnerabilities", https://junglewise.ai/threats/technologies/praisonai, 26 September 2026.