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.
Fix
Nothing published yet: no patch, vendor advisory or mitigation reference on NVD, no vendor advisory in the News for this CVE, not in CISA's KEV, no fixed package version. BaselineWatch does not guess at one.
Public exploits 1
- PraisonAI praisonaiagents 1.6.77 - Remote Code Execution (remote · multiple) Exploit-DB · 2026-08-11
Each line links to the index that lists it, never to exploit code. Exploit-DB's "verified" and a Metasploit rank of good or better count as verified; a PoC-in-GitHub entry is a repository's claim.
Change history 1
- First seenCVSS 10.0NVD modified 2026-10-25 15:10
Affected (CPE criteria) 0
NVD has not attached CPE configurations yet.