CVE-2026-61447
Published: July 11, 2026•Last Modified: July 11, 2026
CVSS SCORE
10.0
CRITICAL
Vulnerability 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 & Versions
No configurations parsed from local entry.
Security Advisories & References
Mitigation & Remediation
Update the affected packages to a secure version. Refer to vendor security advisories.
Share Advisory
Copy the standardized markdown formatted vulnerability report to post in Slack, Teams, email, or ticketing systems.
# CRITICAL - CVE-2026-61447
## EFFECT
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
Unknown products
## LINKS
- [github.com](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw)
- [www.vulncheck.com](https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent)
## SOLUTION
- Update the affected packages to a secure version. Refer to vendor security advisories.