ClawHub
Back to skill

Security audit

Expert Role

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only expert-style writing and reasoning aid with no code execution or system access, but its expert persona should not be treated as real credentials.

Safe to install as a response-style aid. Use extra caution for financial, legal, medical, security, or other high-impact advice, and verify claims with reliable sources or qualified professionals rather than relying on the simulated expert role.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broad enough to match many ordinary requests that ask for 'deep' or 'professional' analysis, which can cause the skill to activate outside its intended niche. Over-broad routing increases the chance that a roleplay-heavy skill overrides more appropriate, policy-constrained skills or injects unnecessary authoritative framing into sensitive tasks.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'when to use' table lists generic categories like complex analysis, professional consultation, decision advice, and high-quality output, all of which are common across normal conversations. Because there are no precise scope boundaries or exclusions, the skill may be selected too frequently, amplifying its instruction set and expert-persona behavior in contexts where it is unnecessary or risky.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.