Investigation First

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:32 PM UTC
• Version:
  1.0.0

Overview

This appears to be a coherent investigation-helper skill with a broad trigger, but no evidence of hidden installation, credential access, persistence, or destructive behavior.

Install if you want an agent to use a structured investigation workflow. Be aware that the trigger may be broad, so you may want to invoke it only for tasks that genuinely need evidence gathering or repository/file inspection.

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: 91% confidence
• Finding: The skill’s activation condition is very broad: it triggers whenever facts are incomplete, evidence is weak, or the domain is unfamiliar, which overlaps with a large share of ordinary reasoning and advisory tasks. This can cause the agent to over-invoke the investigation workflow, increasing prompt-surface area, tool use, and opportunities for unintended behavior or instruction interference, even though the content itself is not overtly malicious.

VirusTotal

65/65 vendors flagged this skill as clean.