ClawHub
Back to skill

Security audit

content-remix

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed Chinese social-media content remix helper with a small API lookup script, but users should avoid sending sensitive drafts to its third-party API.

Install this only if you want Chinese social-platform content rewriting and rule lookup. Review compliance checks manually, especially for regulated products or advertising claims, and do not submit confidential drafts, unreleased campaigns, or regulated content to the external API unless you are comfortable with that third-party service handling it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger phrases are very broad and overlap with ordinary marketing/content requests, which can cause the skill to activate in situations broader than the user intended. Over-broad invocation increases the chance that sensitive user content is routed into this skill and potentially to its external API backend without explicit user awareness.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes a real third-party API backend and specific endpoints, but it does not warn users that supplied content may be sent off-system. This creates a clear data exposure risk: users may submit proprietary drafts, marketing plans, or regulated content believing processing is local when it may be transmitted to an external service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.