Back to skill

Security audit

OpenClaw Git Backup

Security checks across malware telemetry and agentic risk

Overview

This skill openly sets up scheduled Git backups that commit and push a chosen repository, which matches its stated purpose but requires careful setup.

Install only for repositories you intentionally want backed up to the configured remote. Confirm the branch, remote, schedule, and exclusion patterns before enabling it; avoid committing secrets; prefer least-privilege or expiring credentials; and remove the cron job or credential file when automated backups are no longer needed.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs storing a GitHub HTTPS token in a repo-local credential file under .git, which creates a persistent local secret without clearly warning the user about its sensitivity, lifetime, or host exposure risks. Although it avoids the worse practice of embedding the token in the remote URL, this still increases the chance of credential theft from disk, accidental backup of the credential store, or misuse by other local processes with access to the repository.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The template explicitly instructs a scheduled workflow to commit and push repository changes and to avoid asking the user questions, but it does not require any warning or confirmation that local repository contents will be modified and transmitted to a remote. In a backup skill, this increases the risk of unintended data exfiltration or committing sensitive files, especially when used with broad repository paths or weak exclusion patterns.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.