auto-daily-summary

• Outcome: Review
• Latest audit: May 29, 2026, 9:24 PM
• Version:
  1.0.1

Overview

This skill appears to do what it says, but it sets up persistent daily automation for every detected agent and uses unsafe shell command construction.

Install only if you want every OpenClaw agent on the system to receive an indefinite daily summary prompt. Before running it, review the affected agents, understand how to list and delete the created OpenClaw cron jobs, and consider editing the script to target specific agents and avoid shell=True command construction.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_openclaw_command(command):
    """Execute openclaw CLI command and return output."""
    try:
        result = subprocess.run(
            command, 
            shell=True, 
            capture_output=True,

• Confidence: 99% confidence
• Finding: result = subprocess.run( command, shell=True, capture_output=True, text=True, timeout=30 )

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill documentation describes automatic setup of daily summary cron jobs for all available agents, but it does not present this side effect as a prominent warning to the user before execution. That omission can lead users to run the skill without realizing it will persistently schedule automated actions across multiple agents, creating surprise automation, privacy concerns, and broad operational impact.

VirusTotal

66/66 vendors flagged this skill as clean.