CVE-2026-61447
CRITICAL
10.0
CVSS 3.1
Description
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.
Metadata
Severity & Metrics
10.0
CRITICAL CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Affected products (1)
| Vendor | Product | Platform | Versions |
|---|---|---|---|
| MervinPraison | PraisonAI | — | 0 < 1.6.78, 1.6.78 |
Weakness (CWE)
| CWE | Source | Description |
|---|---|---|
| CWE-94 | cna | Improper Control of Generation of Code ('Code Injection') |
CVSS scores (2)
| Score | Severity | Version | Source | Vector |
|---|---|---|---|---|
| 10.0 | CRITICAL | 4.0 | cna | 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 |
| 10.0 | CRITICAL | 3.1 | cna | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
References (2)
- GitHub Security Advisory (GHSA-2xv2-w8cq-5gxw) https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw
- VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via CodeAgent https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent