clawhub-skill-install

Security checks across malware telemetry and agentic risk

Overview

This skill openly automates ClawHub skill installation, but it bypasses normal safety prompts and keeps retrying installs, including warning-flagged ones.

Install only if you intentionally want an agent to install ClawHub skills on your behalf. Review each target skill yourself first, and avoid using this helper for untrusted or warning-flagged skills because it passes `--force` automatically and can retry for up to 30 minutes.

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
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly advertises automatic confirmation of installs using --force but does not warn the user that this may bypass safety prompts, including installs flagged as suspicious. That creates a meaningful trust and consent problem: a user may invoke a routine installer while the agent silently overrides protective checks and proceeds with potentially unsafe code.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal