ClawHub
Back to skill

Security audit

Little7 Bcdr

Security checks across malware telemetry and agentic risk

Overview

This is a transparent backup skill, but it can copy private Little7/OpenClaw state and allowlisted secrets into Google Drive backup archives.

Before installing or using this skill, review LITTLE7_WORKSPACE_ROOT, LITTLE7_GDRIVE_BASE, any cron entries, and any LITTLE7_SECRET_PATHS_FILE or docs/LITTLE7_SECRET_PATHS.txt allowlist. Use it only for destinations you control, and consider encrypting or separately protecting archives that contain identity, memory, keys, tokens, or other secrets.

SkillSpector

By NVIDIA
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
87% confidence
Finding
The skill explicitly instructs agents to prefer silent success for cron-driven backups while also describing archive creation and retention pruning. In a backup/automation context, silent operation can be operationally reasonable, but without an explicit requirement for prior user consent, visible setup-time disclosure, or audit logging, it increases the risk of unnoticed filesystem changes and unintended data retention/deletion behavior.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This script packages files listed in an allowlist of secret paths into a separate archive and writes both archives to a Google Drive-synced directory automatically, with no interactive warning, confirmation, encryption, or permission hardening. Even though the behavior is intentional for BC/DR, it materially increases the chance of credential exposure through sync misconfiguration, compromised cloud accounts, shared folders, or backups being restored onto less-trusted systems.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.