ClawHub

Niche Twitter

Security checks across malware telemetry and agentic risk

Overview

This is mostly a coherent Twitter/X research and content skill, but it encourages under-scoped recurring monitoring and includes an unnecessary local execution step.

Review before installing. Use it only for explicit Twitter/X research or drafting tasks, do not allow recurring monitoring unless you set the exact query, schedule, notification target, end date, and disable procedure, and avoid running the missing formatter command unless you inspect or supply a safe script yourself.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs execution of a shell command for formatting generated Twitter content, even though the skill’s stated purpose is research and content generation. Introducing command execution expands the attack surface unnecessarily: if user-controlled content is interpolated into the command, it can enable command injection or unsafe local code execution in environments that honor skill instructions.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger criteria are broad and include vague phrases like implied mentions and generic goals such as growth, leads, and research, which can cause the skill to activate for unrelated requests. Over-broad activation increases the chance of unintended tool use, scope creep, and execution of higher-risk instructions such as web searches or shell-adjacent actions in contexts where the user did not specifically request this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal