ClawHub
Back to skill

Security audit

🧠 Requirement Comprehension Engine

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed planning and skill-routing helper, with no executable install hooks or hidden data-transfer behavior found.

Install this only if you want an orchestration layer that may decompose complex requests and route them through other skills. Review the required companion skills because they determine the actual memory, logging, cleanup, and delegated authority.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger description is very broad (e.g., multi-intent, ambiguous instructions, multiple skill domains), which increases the chance this orchestration skill is invoked for many unrelated requests. Because this skill can influence downstream skill selection, sequencing, and delegation, unintended activation can alter agent behavior, expand attack surface, and enable prompt-routing mistakes or policy bypass via over-orchestration.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.