ClawHub
Back to skill

Security audit

Security Audit

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Move contract security checklist with no hidden execution, credential use, persistence, or external data flow in the artifacts.

Safe to install as audit guidance. Treat it as a checklist, not a guarantee of contract safety, and verify the publisher before relying on the metadata claim of Aptos Labs authorship.

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 list includes very broad phrases such as 'security check', 'review security', and 'is this secure', which can cause the skill to activate in routine conversations that were not intended to invoke a deployment-grade Move contract audit workflow. In an automated agent environment, unintended invocation can lead to confusing behavior, wasted resources, or accidental execution of audit-related steps in the wrong context, even though the skill itself is security-focused rather than overtly malicious.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.