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.
Problem types
Improper Control of Generation of Code ('Code Injection')
Product status
Any version before 1.6.78
1.6.78 (semver)
Credits
anushkavirgaonkar
References
github.com/...isonAI/security/advisories/GHSA-2xv2-w8cq-5gxw (GitHub Security Advisory (GHSA-2xv2-w8cq-5gxw))
www.vulncheck.com/...ore-remote-code-execution-via-codeagent (VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via CodeAgent)