ClawHub
Back to skill

Security audit

Startups

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, read-only startup research helper, but users should treat the optional Moltbook identity header as a credential sent to startups.in.

Install if you are comfortable sending startup research queries and startup names to startups.in. Do not provide a Moltbook identity token unless you need enhanced access and trust startups.in to receive and handle that identity token.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
97% confidence
Finding
The skill explicitly instructs users to send a Moltbook identity token to a third-party domain (startups.in) without any warning about the trust boundary, what data the token conveys, or whether the service is authorized to receive it. This can lead to inadvertent credential disclosure, account correlation, or misuse of delegated identity data, especially because the token is presented as a normal enhancement rather than a sensitive action.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.