Nm Imbue Structured Output

• Outcome: Pass
• Latest audit: Jun 19, 2026 at 2:33 PM UTC
• Version:
  1.9.12

Overview

This skill only provides structure for formatting reports and review deliverables, with no evidence of hidden execution, data access, or destructive behavior.

Install this if you want an agent to standardize final reports and review outputs. Be aware that generic formatting requests may activate it, so review final wording when another task’s exact output style matters.

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: 85% confidence
• Finding: The trigger keywords and contextual cues are broad enough that the skill may auto-activate during many ordinary requests involving formatting, reporting, or presentation. In an agent system, unintended invocation can alter workflow, inject extra instructions, or bias outputs away from the user's primary task; while this skill is not overtly malicious, broad activation increases the attack surface and can compound risk when combined with other skills or automation.

VirusTotal

63/63 vendors flagged this skill as clean.