CVE-2026-61447
PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
- State
- Published
- Severity
- 10.0 Critical
- Published
- Jul 11, 2026
- Updated
- Jul 13, 2026
- Reserved
- Jul 9, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 10.0 Critical | 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 | VulnCheck |
| 3.1 | 10.0 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H | VulnCheck |
Weaknesses
- CWE-94 Improper Control of Generation of Code ('Code Injection')
Affected Products
| Product | Versions |
|---|---|
PraisonAIMervinPraison |
|
References
- GitHub Security Advisory (GHSA-2xv2-w8cq-5gxw)vendor-advisory
- VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via CodeAgentthird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.