ClawHub
Back to skill

Security audit

targeted-tech-research

Security checks across malware telemetry and agentic risk

Overview

This is a coherent technical research skill with disclosed web-research behavior and local helper scripts, but users should manage retained evidence and metadata carefully.

Install only if you are comfortable with public web research, occasional dynamic browsing, and local audit artifacts. Do not provide confidential PDFs, patents, or business documents unless you are prepared to review and delete the generated evidence and execution metadata afterward.

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 (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill specifies automatic saving of scraped evidence and execution metadata to local storage without clear user notice, consent, retention limits, or handling rules. That creates a real privacy and data-governance risk because scraped content, user inputs, URLs, and operational metadata may persist beyond the session and be accessible to other users, tools, or logs.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs processing of user-provided private PDFs/patents and extraction of fields from execution metadata without any privacy warning or safeguards. In this context, private technical documents may contain confidential business information, and silently ingesting, compressing, and reusing that material increases the risk of unintended disclosure or over-retention.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The wildcard domain patterns `docs.*.com` and `developer.*.com` are overly broad and can match many unrelated domains, causing the Playwright scraper to run on sites that were not intentionally approved. In a whitelist that controls expensive or privileged scraping behavior, this weakens scope restriction and can increase attack surface, resource consumption, and the chance of interacting with untrusted dynamic content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.