ClawHub

SaaS Project Bootstrap

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only project bootstrap skill that discloses the agent and documentation files it creates, with no hidden code, credential use, or network behavior found.

Install this only in a repository where you want persistent AI workflow files added. Use a clean git branch, review AGENTS.md, .agents files, and docs/templates before committing, and be cautious with the placeholder references to a separate starter repo unless you inspect that source first.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README states that the skill will create files inside the target project, but it does not clearly warn users that running it will modify the workspace. This can lead to unexpected file creation or overwriting in an existing repository, which is especially risky for users applying the skill to real production codebases.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger guidance is broad enough to activate on many generic project-initialization requests, which can cause the skill to be selected outside its narrow intended scope. In an agentic environment, overbroad activation increases the chance of unnecessary file creation or workflow scaffolding being applied to repositories where the user did not explicitly want this operating layer.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest description uses very broad terms like bootstrapping 'any SaaS, dashboard, mobile, or API project,' which makes the skill appear applicable to a wide range of normal development tasks. This can lead to unintended invocation precedence over more specific skills, causing scope creep and unrequested repository changes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal