ClawHub

Scroll

Security checks across malware telemetry and agentic risk

Overview

This skill is not dangerous code, but it is marketed as Scroll blockchain guidance while mostly providing generic placeholder finance and operations text.

Review before installing if you need accurate Scroll guidance. The script appears technically low-risk, but users should not rely on it for blockchain operations, finance, compliance, security, or protocol decisions without checking authoritative Scroll documentation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The script presents itself as a Scroll blockchain reference tool, but the actual content is generic placeholder material unrelated to Scroll. This is dangerous because users or downstream agents may rely on it for blockchain-specific guidance and make incorrect operational, security, or compliance decisions based on misleading documentation.

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The inline documentation explicitly claims the tool is for Scroll in blockchain contexts, but the commands do not deliver Scroll-specific blockchain information. In an agent skill context, this mismatch increases the risk of misinformation, causing users or automated systems to trust and surface irrelevant guidance under a credible blockchain label.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The 'When to Use' guidance is broad and overlaps with generic blockchain assistance rather than narrowly scoping the skill to Scroll-specific tasks. In an agent routing context, this can cause the skill to activate for unrelated blockchain requests, leading to inappropriate tool use, reduced answer quality, and possible misuse of domain-specific guidance in the wrong context.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal