ClawHub
Back to skill

Security audit

OMIE Energy

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to support OMIE energy scheduling, but its optional control mode can run arbitrary user-supplied shell commands, so it needs careful review before installation.

Install only if you intend to use local automation commands and understand that enabling --execute can run whatever command string is passed. Keep dry-run mode unless you have reviewed the exact commands, avoid untrusted inputs, and prefer a dedicated low-privilege account or tightly allowlisted smart-home commands.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_cmd(label: str, cmd: str, execute: bool):
    print(f"{label}: {cmd}")
    if execute:
        subprocess.run(cmd, shell=True, check=True)


def command_control(args, default_area: str):
Confidence
99% confidence
Finding
The code executes a caller-provided string with subprocess.run(..., shell=True), which allows arbitrary shell execution in the context of the user running the skill. In this skill, the command comes from CLI arguments intended for smart-home control, so any untrusted or mistaken input can trigger arbitrary OS commands, not just constrained device actions.

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill explicitly instructs users to run shell commands (`bash run.sh ...`), read environment/config files, and pass arbitrary `--on-command`/`--off-command` strings that are later executed. Even though these capabilities are central to the skill's purpose, the absence of declared permissions means users and tooling are not clearly informed that the skill can execute shell commands and access local configuration, which increases the risk of unsafe use or privilege misuse.

Context-Inappropriate Capability

High
Confidence
95% confidence
Finding
The skill’s stated purpose is energy-price retrieval and scheduling advice, but it also exposes a generic command-execution capability for 'on' and 'off' actions. That broad capability materially increases risk because the skill can be used as a launcher for arbitrary local system actions unrelated to OMIE pricing.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill can execute external commands that may affect the host or connected devices, and the only guard is a dry-run default plus an --execute flag. In an agent or automation setting, this is insufficient because users may not understand that enabling execution grants the skill the ability to run arbitrary shell commands.

Static analysis

No suspicious patterns detected.