ClawHub
Back to skill

Security audit

Publish npm + ClawHub

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed publishing helper that performs local release checks and guides explicit npm/ClawHub publishing steps.

Install only if you want an agent to help with real release workflows. Keep `config/publish.accounts.local.json` gitignored, review the files copied into the temporary release directory, use a disposable output path such as `/tmp/publish-release`, and treat `npm publish` / `clawhub publish` as state-changing commands that should be run only with explicit intent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly requires Read, Write, Bash, plus external tools like clawhub and curl, but does not declare permissions in a machine-readable way. This creates a transparency and consent gap: an agent may invoke file, shell, and network-capable actions without clear least-privilege boundaries, increasing the chance of unintended data exposure or command execution during publishing workflows.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The README gives concrete publish steps for npm and ClawHub but does not clearly warn that later workflow steps perform external network publication and can change package state. In a release-oriented skill, lack of an explicit warning can lead to unintended publication by an agent or user who treats the workflow as a dry-run or local-only process.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal