Safe Config Modifier

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.0

Overview

This skill is meant to safely edit OpenClaw configuration, but its secret-masking helpers can fail and may expose API keys or tokens during preview.

Install only if you are comfortable letting the skill read and change your core OpenClaw configuration. Do not rely on its preview scripts to hide secrets; manually redact API keys and bot tokens before sharing output, review the exact diff before using the confirmation phrase, and keep the backup files private.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The document includes realistic token and API key configuration examples for Telegram, Kimi, Brave, and web search without adjacent guidance on secret handling, redaction, storage hygiene, or avoiding accidental sharing. In the context of a skill specifically designed to modify ~/.openclaw/openclaw.json, this increases the chance users will paste real credentials into configs, logs, screenshots, or commit history, leading to credential leakage.

VirusTotal

66/66 vendors flagged this skill as clean.