Deep Research

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:43 AM UTC
• Version:
  0.1.0

Overview

This skill is a transparent deep-research writing workflow that uses web sources and local markdown drafts without hidden execution or credential access.

Install this if you want an agent to perform exhaustive cited research. Set clear limits on topic scope, source types, browsing depth, languages, output length, and whether it may create intermediate markdown draft files in your workspace.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger description is broad enough to activate on many ordinary requests for analysis, reports, or thorough explanations, which can cause the agent to invoke an expensive and highly capable research workflow when it is unnecessary. Over-broad triggering increases the attack surface for prompt steering, unnecessary web access, excessive tool use, and policy drift because the skill may engage in multi-step external research for benign requests that do not require it.

VirusTotal

66/66 vendors flagged this skill as clean.