software_test_case_design

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 2:29 AM UTC
• Version:
  1.0.5

Overview

This is a text-only test-case design skill with some broad routing terms, but no evidence of hidden execution, data access, persistence, or exfiltration.

Install this if you want broad assistance drafting software test cases. Be aware that generic prompts mentioning agents or web testing may activate it when a narrower skill would be better; it should not need credentials or run tests for you.

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 (3)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The manifest description is extremely broad and enumerates many common testing activities, which can cause the skill to be selected for a wide range of ordinary requests beyond the author's likely intent. Over-broad routing increases the chance of capability confusion, inappropriate instruction loading, and unexpected behavior in downstream agent workflows.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: Using the standalone keyword "Agent" as a trigger is dangerously generic because it can match many unrelated user prompts that merely mention agents, customer service agents, or software agents. This can misroute requests into the wrong skill, causing irrelevant instructions and checklists to be loaded and potentially overriding safer or more appropriate routing decisions.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The platform trigger "Web Testing" is ambiguous and broad enough to capture many requests that are not specifically about PC web platform behavior. That ambiguity can lead to incorrect platform overlay selection, producing mismatched test cases and reducing reliability of the skill's outputs.

VirusTotal

64/64 vendors flagged this skill as clean.