ClawHub
Back to skill

Security audit

Hot Content Writer

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it claims, but its API mode can quietly reuse an existing OpenAI API key and send it to the configured DeepSeek/OpenAI-compatible endpoint.

Review before installing if your environment has API keys. Prefer a dedicated low-privilege DeepSeek key, use environment variables or a local-only config file, verify OPENAI_API_BASE before using API mode, and unset unrelated OPENAI_API_KEY values if you do not want this skill to use them. Only use hot-topic modes with companion hot-list skills you trust.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instructions tell users to place a live DeepSeek API key in config.json but provide no warning about secret leakage, file permissions, accidental commits, or safer alternatives. This is dangerous because config files are commonly checked into version control or shared, which can expose the API key and allow unauthorized API use and billing abuse.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The code writes hot-topic data to a fixed path under C:\tmp, which creates predictable filenames and leaves intermediate data on disk. A local attacker or another process could read, overwrite, or race these files, causing data leakage or poisoning of the topics later consumed by this workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.