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.
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}")
# 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(...)
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.
{
"cwe_ids": [
"CWE-78"
],
"github_reviewed": true,
"severity": "CRITICAL",
"github_reviewed_at": "2026-04-01T23:20:00Z",
"nvd_published_at": "2026-04-03T23:17:05Z"
}