CVE-2026-61447

critical · 10

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

2.5%

EPSS (exploit prob.)

84th

EPSS percentile

2026-07-11

Published

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Weaknesses

CWE-94

References

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw
https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2026-61447