What’s Vulnerable › Vulnerabilities

CVE-2026-34935: PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

• Severity: critical (CVSS 9.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.8% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2026-04-03 · updated 2026-07-24
• Weakness: CWE-78

Description

PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.

Affected products

• MervinPraison PraisonAI: from 4.5.15 before 4.5.69 — fixed in 4.5.69

How to fix

Upgrade to a fixed version: MervinPraison PraisonAI 4.5.69. Check the vendor advisory for mitigations.

References

• https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m

Get alerted when CVE-2026-34935 or the next vulnerability affects your stack