ClawHub
Back to skill

Security audit

CTQ分析技能

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local customer-feedback analysis tool, with expected file reads and report generation but no hidden network, credential, destructive, or persistence behavior.

Before using this skill, redact unnecessary personal, account, or regulated data from customer feedback and store generated JSON/HTML reports in an appropriate location. Treat generated HTML reports as containing customer-derived content and review them before sharing outside the intended audience.

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
89% confidence
Finding
The trigger conditions are broad enough to match many generic analysis requests, which can cause the skill to activate in situations where the user did not intend customer-feedback processing. Unintended invocation matters because the skill reads local files, processes potentially sensitive text, and generates derivative reports, increasing the chance of inappropriate data handling or workflow confusion.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
Customer feedback commonly contains personal data, account details, contact information, or sensitive complaints, yet the skill does not warn users to minimize, redact, or handle such data carefully before analysis and HTML report generation. This omission can lead to privacy exposure, overcollection, and unsafe persistence of sensitive content in output artifacts that may be shared broadly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.