ClawHub

AI Startup MVP Factory

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent MVP automation workflow, but it can trigger broad repository, wiki, container, and deployment-related actions without clear approval gates or scoping.

Install only if you intend to run an end-to-end MVP automation pipeline. Before using it, confirm the target repository, wiki space, registry, credentials, and whether each external action should be dry-run, local-only, or actually published.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README advertises an end-to-end workflow that can generate code, push to GitHub, run AI review, sync knowledge bases, and produce deployment artifacts, but it does not clearly warn users about privacy, credential handling, repository modification, or deployment-side effects. In an agent setting, this omission can lead users to authorize broad actions on source code, secrets, and infrastructure without informed consent, increasing the risk of unintended disclosure or system changes.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad, generic product-building terms such as '创建MVP', '创业项目', and '从零开始写项目', which can match many ordinary requests and cause this high-impact automation workflow to activate unintentionally. Because the skill orchestrates code generation, PR creation, CI/CD, and deployment preparation, accidental activation could lead to unintended repository or infrastructure-affecting actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill describes automated PR creation, wiki sync, image pushing, and deployment artifact generation without clearly warning that these actions may modify repositories, publish artifacts, or affect deployment environments. In a workflow explicitly designed to move from idea to production-ready output, omission of these warnings increases the risk that users invoke side-effectful operations without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal