PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
48Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 10epss 2.5%
from disclosure to weapon31 days
Published on NVDJul 11
1st PoC+31d
exploitation probability
2.5%top 16% of all CVEs
observed exploitation
nono source reports it
1 public exploit(s)
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.
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
Affected products
MervinPraison · PraisonAIpublic PoCs found — 1
exploitdbwww.exploit-db.com/exploits/52639unverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.