ClawHub
Back to skill

Security audit

Bring! Shopping List

Security checks across malware telemetry and agentic risk

Overview

The skill set is mostly coherent, but it includes powerful staff/admin workflows and a review helper that defaults to unsandboxed full-access execution.

Install only in a trusted ClawHub staff/developer context. Review the `autoreview` helper before use, prefer `--no-yolo` unless full-access nested review is truly intended, and confirm that any admin or migration command targets the right account, package, deployment, and data before approving it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/bring.sh:12