ClawHub
Back to skill

Security audit

Nccl Optimizer

Security checks across malware telemetry and agentic risk

Overview

This skill has a legitimate NCCL benchmarking purpose, but its optional node input can be inserted into a shell command without validation.

Review before installing. Use it only on GPU hosts or clusters you are authorized to benchmark, avoid passing untrusted node names, and prefer a fixed version that validates nodes and avoids shell=True before enabling automatic inter-node benchmarking.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def _run_cmd(cmd: str, timeout: int = 60) -> str:
    """Run *cmd* via shell, return stdout+stderr stripped; empty string on any failure."""
    try:
        return subprocess.check_output(
            cmd, shell=True, stderr=subprocess.STDOUT, text=True, timeout=timeout
        ).strip()
    except Exception:
Confidence
98% confidence
Finding
return subprocess.check_output( cmd, shell=True, stderr=subprocess.STDOUT, text=True, timeout=timeout ).strip()

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to execute shell commands such as nvidia-smi, ibv_devinfo, all_reduce_perf, p2p_bw, and mpirun, but the skill declares no permissions. That mismatch is a real security issue because shell execution and local file/environment access expand the agent's capabilities without transparent consent or policy enforcement, especially on multi-user or production training nodes.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
def _run_cmd(cmd: str, timeout: int = 60) -> str:
    """Run *cmd* via shell, return stdout+stderr stripped; empty string on any failure."""
    try:
        return subprocess.check_output(
            cmd, shell=True, stderr=subprocess.STDOUT, text=True, timeout=timeout
        ).strip()
    except Exception:
Confidence
99% confidence
Finding
subprocess.check_output( cmd, shell=True

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.