ClawHub

Content Brainstorm 自媒体选题策划

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese social-media writing helper with no evidence of hidden access, persistence, credential use, or automatic posting.

Install this if you want help drafting Chinese social-media posts. Confirm the target platform and language before using it for general writing, and review any generated claims, citations, marketing language, and platform compliance before publishing.

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 activation triggers are broad enough to match generic phrases like 'brainstorm' or 'what to write', which can cause the skill to activate outside its intended scope. Over-broad routing can lead to inappropriate data collection prompts, user confusion, or unintended invocation of web research behavior when the user did not ask for this specific skill.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill hard-codes a Chinese social media and language focus without clearly presenting this as an opt-in constraint, which can cause mismatch between user intent and skill behavior. While not an exploit in the traditional sense, it can produce inappropriate recommendations, platform assumptions, or accidental localization bias if invoked for users expecting broader coverage.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal