ClawHub
Back to skill

Security audit

X Algorithm

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only social media strategy skill, with no code execution or data access, though it may encourage aggressive engagement tactics.

Install only if you want an agent to help draft engagement-optimized X/Twitter content. Review outputs before publishing, especially content using urgency, FOMO, controversy, or reply-farming tactics, and ensure posts comply with platform rules and your brand standards.

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

Low
Confidence
87% confidence
Finding
The skill explicitly optimizes for engagement using tactics like controversy, reply farming, and avoiding links to maximize reach, but it provides no guardrails about manipulation, platform policy, or reputational risk. In context this is not a code-execution or data-exfiltration issue, but it can still steer agents or users toward spammy, deceptive, or brand-damaging behavior at scale.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.