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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| MervinPraison | PraisonAI | < 1.6.78 | 1.6.78 |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
Third-party code, not reviewed by us. Public PoCs are sometimes fake or contain malware. Read the code first and run it only in an isolated lab, against systems you are authorised to test.
Exploit-DB 1
- PraisonAI praisonaiagents 1.6.77 - Remote Code Execution EDB-52639 · remote · Aug 11, 2026
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | praisonaiagents | < 1.6.78 | 1.6.78 | GHSA-2xv2-w8cq-5gxw |
References
- GitHub Security Advisory (GHSA-2xv2-w8cq-5gxw) vendor-advisory
- VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via CodeAgent third-party-advisory