ClawHub

Competitor Spy Tool

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches competitor-monitoring use, but it includes advice to work around blocking with rotating user agents and residential proxies.

Install only if you will keep monitoring limited to public pages you are allowed to access, use scoped API keys and dedicated Slack/Sheets destinations, and define domain, frequency, retention, and deletion limits. Do not use the proxy-rotation or User-Agent-rotation advice to continue scraping a site that has blocked automated access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The skill’s safety section claims it will respect robots.txt, avoid bypassing access controls, and use ethical monitoring only, but the troubleshooting guidance explicitly recommends rotating user agents and residential proxies when a target blocks automated requests. That contradiction materially increases risk because it instructs users how to evade anti-bot defenses and continue scraping after a site has signaled blocking, which can cross legal, contractual, and policy boundaries.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill describes capturing screenshots, storing HTML snapshots, sending alerts to Slack, and logging data to Google Sheets, but it does not clearly warn users that monitored third-party website content may be copied, retained, and transmitted to external services. This is dangerous because users may unknowingly export collected data outside the local environment, creating privacy, confidentiality, retention, and compliance risks even if the source content is public.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description is broad enough to match generic requests for market research, monitoring, or SEO analysis, which can cause the skill to activate in situations where the user did not intend web scraping, persistence, or external transmission. In context, that is risky because this skill includes competitor monitoring, screenshot capture, keyword tracking, Slack alerts, and data logging, so overbroad invocation can lead to unnecessary collection and sharing.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal