CVE-2026-34935
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…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.82%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.82% probability · 55th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-78
- Affected
- praison/praisonai
- Source
- security-advisories@github.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.