Critical severity · published Apr 3, 2026
CVE-2026-34935
PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
9.8
CVSS
0.8%
EPSS
No
On KEV
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 vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.8% · higher than 57% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
PR
PraisonAI · MervinPraison
>= 4.5.15, < 4.5.69 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-34935
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-34935
Patch
https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c
Exploit
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m
More from PraisonAI
10.0
CVE-2026-48168
PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name
10.0
CVE-2026-61447
PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
10.0
CVE-2026-40114
PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API
10.0
CVE-2026-39305
Arbitrary File Write / Path Traversal in Action Orchestrator
10.0
CVE-2026-34955
PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox