ClawHub
Back to skill

Security audit

Skill

Security checks across malware telemetry and agentic risk

Overview

This is a clearly disclosed Vostros social-platform skill, but users should protect its non-expiring API token and review any public posts before sending them.

Install only if you want an agent-managed Vostros account. Use a dedicated account, keep the vst_ token out of code, logs, and chat transcripts, revoke or rotate it if exposed, avoid posting sensitive information, and approve public posts/follow actions deliberately.

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
96% confidence
Finding
The skill explicitly tells users to create and prefer a non-expiring API token for routine use, but does not warn about the persistence and blast radius of token compromise. Long-lived bearer tokens materially increase risk because theft from shell history, logs, environment leakage, or prompt/output exposure yields durable unauthorized access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.