Skip to content
Threat Brief

← All advisories

CVE-2026-34935

Critical 9.8No known exploitationFix available

PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

Vendor advisory: GHSA-9gm9-c8mq-vq7m

Record last updated

CVSS score

9.8

Critical on a 0 to 10 scale

EPSS, chance of exploitation in 30 days

None

No EPSS score available

CISA remediation deadline

None

Not in the KEV catalog

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.

Weakness: CWE-78

Patching and mitigation

Patch status
Fix available (source: GitHub Advisory Database)
Fix documented (source date)
Mitigation
None documented
Vendor guidance
github.com (opens in a new tab)

Affected products

VendorProductAffected versionsFixed inPer
MervinPraisonPraisonAI>= 4.5.15, < 4.5.69Not documentedCVE Program
pippraisonaifrom 4.5.15 before 4.5.694.5.69GitHub Advisory Database

Timeline

  1. Disclosure

    CVE record published by GitHub_M

    Source: CVE Program (opens in a new tab)

  2. Patch

    Fix documented by GitHub Advisory Database

    Source: GitHub Advisory Database (opens in a new tab)

Vendor guidance and references