ClawHub
Back to skill

Security audit

答案之书

Security checks across malware telemetry and agentic risk

Overview

This is a small novelty “answer book” skill that returns a random Chinese phrase and does not access files, credentials, or the network.

Install this only if you want a novelty oracle-style answer generator. Because some trigger phrases are broad, invoke it by name when possible, and do not treat its random output as reliable guidance for important personal, financial, medical, or legal decisions.

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
91% confidence
Finding
The trigger phrases are broad natural-language expressions such as asking for guidance, destiny, or an answer, which can cause the skill to activate when the user did not specifically intend to invoke this skill. This can lead to misrouting of user requests and inappropriate oracle-style responses in unrelated contexts, reducing reliability and potentially interfering with safer or more relevant skills.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.