Shadows Deep Research

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  1.1.0

Overview

This is a single-file research workflow prompt with no executable code, persistence, credentials, or privileged access.

Install this if you want a structured four-round research process. Be aware it can be invoked by broad analysis wording, and research queries may be sent through the agent's normal search provider when the agent has search available.

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: 90% confidence
• Finding: The trigger conditions are broad and include generic phrases like 'analyze thoroughly' and 'complex problem with no obvious solution', which can cause the skill to activate for many normal requests. Over-broad activation can unexpectedly steer the agent into a long, rigid workflow, increasing prompt-surface area and potentially interfering with user intent or higher-priority safeguards.

VirusTotal

66/66 vendors flagged this skill as clean.