ClawHub
Back to skill

Security audit

Context Onboarding

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a local workspace-onboarding helper that reads user-selected files, with no evidence of hidden exfiltration or destructive behavior.

Install only if you are comfortable with the agent reading the files you select. Keep `--workspace` and `--files` pointed at trusted project documents, and do not include secrets, SSH keys, tokens, private configs, or unrelated system paths.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_workspace(args, workspace):
    return subprocess.run(
        [sys.executable, str(SCRIPT_PATH)] + args,
        capture_output=True,
        text=True,
Confidence
70% confidence
Finding
return subprocess.run( [sys.executable, str(SCRIPT_PATH)] + args, capture_output=True, text=True, cwd=workspace, )

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This markdown file describes behavior that reads and displays the first lines of selected documents, and it explicitly allows users to add extra files and point at another workspace. Because this can expose contents of user data or sensitive workspace documents, the skill description should include a clear warning about reviewing file choices and avoiding sensitive files.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.