ClawHub
Back to skill

Security audit

Generate Tests

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Move testing skill with a minor risk that its generic triggers may activate outside Aptos/Move work.

Use this when you are working on Aptos Move contracts. Be aware it may be invoked for generic testing prompts, and treat the 100% coverage rule as strict quality guidance rather than a complete security guarantee.

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
94% confidence
Finding
The trigger phrases are very broad and match common developer requests like 'create tests' or 'how to test', so this skill may activate in situations where the user did not intend to invoke it. In an agent system, ambiguous invocation can cause the wrong skill to run, leading to misleading outputs, workflow hijacking, or accidental suppression of more appropriate security- or context-specific guidance.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.