---
cve: "CVE-2026-61447"
severity: "CRITICAL"
cvss: 10.0
epss: "2.2%"
vendor: "mervinpraison"
kev: false
exploited: false
published: "2026-07-11 14:16:23"
tags: [cve, security, critical]
source: tsecurity.de CVE-Dossier
exported: "2026-09-03T00:31:27+02:00"
---

# CVE-2026-61447

> 10.0 CRITICAL · 🧪 PoC

## Beschreibung

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

## CVSS-Vektor

```
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Keine | bad |

## Exploit-Evidenz

- [EDB-52639 — PraisonAI praisonaiagents  1.6.77 - Remote Code Execution](https://www.exploit-db.com/exploits/52639)

## Referenzen

- <https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw>
- <https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-61447) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_