ClawHub

technical-research

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed technical research workflow that browses public sources and writes Markdown reports, with no evidence of hidden code, credential access, or destructive behavior.

Install this if you want a heavyweight technical research workflow that uses live web sources and saves several Markdown files. Run it in an appropriate workspace, avoid sensitive topic names if local paths matter, and review generated sources before relying on the report for 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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger description is broad enough to activate on common phrases like '调研'、'研究'、'了解' a technology area, which can cause the skill to run when the user did not explicitly intend this workflow. In an agent setting, over-broad activation increases the chance of unintended web access, multi-step processing, and downstream file creation based on casual user wording.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to create a directory tree and multiple Markdown files under research/{topic}/, but it does not warn the user or require confirmation before modifying the filesystem. In an agent environment, silent writes can overwrite existing work, leak sensitive topic names into local storage, or create persistent artifacts the user did not expect.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal