INCIDENT MAP

Browse / MCP and Tool Server Flaws / CVE-2026-34935

PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

CVE-2026-34935 ยท 2026-04-01 critical

Class
MCP and Tool Server Flaws (filed by a model that read the advisory)
Technique
Code and command execution
Affected
praisonai (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
0.8% chance of exploitation in 30 days

How it works, in short

The PraisonAI CLI passes the --mcp argument to a process launcher without validation, so any supplied command runs as the user. (Our summary, written by a model. The source text is below.)

Details

Summary

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.

Details

cli/features/mcp.py:61 (source) -> praisonaiagents/mcp/mcp.py:345 (hop) -> mcp/client/stdio/__init__.py:253 (sink)

# source
parts = shlex.split(command)

# hop
cmd, args, env = self.parse_mcp_command(command, env_vars)
self.server_params = StdioServerParameters(command=cmd, args=arguments)

# sink
process = await anyio.open_process([command, *args])

Fixed in commit 47bff65413beaa3c21bf633c1fae4e684348368c (v4.5.69) by introducing a command allowlist:

ALLOWED_COMMANDS = {"npx", "uvx", "node", "python"}
if cmd not in ALLOWED_COMMANDS:
    raise ValueError(f"Disallowed command: {cmd}")

PoC

# tested on: praisonai==4.5.48
# install: pip install praisonai==4.5.48
# run: praisonai --mcp "bash -c 'id > /tmp/pwned'"
# verify: cat /tmp/pwned
# expected output: uid=1000(...) gid=1000(...) groups=1000(...)

Impact

Any deployment where the --mcp argument is influenced by untrusted input is exposed to full OS command execution as the process user. No authentication is required.

References

Source: GitHub Advisory Database, used under CC BY 4.0.