ClawHub
Back to skill

Security audit

Find 1.0.0

Security checks across malware telemetry and agentic risk

Overview

This is a simple search-process skill that may encourage broader searching, but it contains no executable code or hidden privileged behavior.

Install this if you want a structured method for hard-to-find information or items. Be mindful that it may lead your agent to search across several external sources, so avoid using it with secrets, credentials, or sensitive personal data unless your agent's browsing and connector permissions are appropriately restricted.

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 description 'Locate anything with progressive search expansion, multi-source validation, and iterative refinement until found' is extremely broad and can be invoked for many ordinary requests, increasing the chance the agent routes unrelated tasks into this skill. Over-broad routing can cause unintended tool use, excessive search behavior, and policy-bypassing workflow selection because the skill claims applicability to 'anything.'

Vague Triggers

Medium
Confidence
88% confidence
Finding
Example triggers such as 'Find me...', 'Where can I get...', and 'I need to find...' are generic phrases that appear in normal conversation, so they may spuriously activate this skill for many unrelated prompts. That broad matching increases the risk of incorrect skill selection, unnecessary browsing/search loops, and reduced adherence to more appropriate specialized skills or safety checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.