CVE-2026-40088 - Vulnerability Analysis

Overview

PraisonAI < 4.5.121 contains a command injection caused by user-controlled input in execute_command function and workflow shell execution, letting attackers inject arbitrary shell commands, exploit requires crafted agent workflows or YAML definitions.

Severity & Score

Impact

Attackers can execute arbitrary shell commands, potentially leading to full system compromise.

Mitigation

Upgrade to version 4.5.121 or later.

References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m
• https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121

Social Media Activity(1 post)

TheHackerWire

@thehackerwire

Apr 10, 2026

🔴 CVE-2026-40088 - Critical (9.6) PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to in... 🔗 https://www.thehackerwire.com/vulnerability/CVE-2026-40088/ #CVE #vulnerability #infosec #cybersecurity #security #Tenda #patchstack

View original post

Related Resources

• Vulnerability Intelligence Dashboard
• Credential Scanner