Agent Errantry Alignment

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:48 PM UTC
• Version:
  1.0.0

Overview

This is a text-only conceptual framework that can shape how an agent discusses AI workflows, but it does not run code or request access to data, credentials, or systems.

Safe to install as a conceptual reference. Be aware that its broad trigger wording may color ordinary agent-design or debugging conversations with the Errantry metaphor, so prefer explicit use when you want that framing and continue to rely on normal approvals, sandboxing, rollback, and domain-specific safety practices for real systems.

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: 93% confidence
• Finding: The manifest description says to use the skill for broad situations like "designing agent workflows," "explaining AI concepts," and "debugging agent behavior," without clear trigger boundaries or exclusion conditions. These are common requests in many normal conversations, so the skill could be invoked unintentionally rather than only in a narrowly defined context.

VirusTotal

63/63 vendors flagged this skill as clean.