Vulnerability · Published Apr 3, 2026 · Assigned by GitHub_M
CVE-2026-34935PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
Critical 9.8
In plain English
A critical-severity OS command injection in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 58% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.5.69 | GHSA-9gm9-c8mq-vq7m |
| PyPI | praisonai | 4.5.69 | PYSEC-2026-471 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | >= 4.5.15, < 4.5.69 |
Weakness: CWE-78 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H