ClawHub

Scifi Writing

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese sci-fi writing helper with no executable code, data access, persistence, or hidden high-impact behavior.

Install this if you want a Chinese-language sci-fi writing assistant. Review the broad trigger wording if you use many writing skills, since it may activate for general sci-fi brainstorming; no evidence shows hidden data access, code execution, persistence, or malicious behavior.

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
94% confidence
Finding
The trigger description is broad enough to match many ordinary requests about science fiction writing, including casual phrasing, which increases the chance of unintended activation. Over-triggering can route users into the wrong skill, causing confusing behavior, policy bypass of intended routing constraints, or accidental disclosure of context to a skill that was not the best match.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill is defined entirely in Chinese and does not provide a user-language negotiation path, which can force responses in a language the user did not request. This is primarily a usability and routing safety issue: users may receive content they cannot verify or may misunderstand important output, especially in multi-skill environments where language expectations should be explicit.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal