Qa Scenario Synthesizer

• Outcome: Pass
• Latest audit: May 29, 2026, 8:24 PM
• Version:
  1.0.0

Overview

This skill is a local QA scenario drafting helper; it has some dormant audit code, but the shipped configuration and instructions keep normal use aligned with generating reviewable test scenarios.

Reasonable to install if you want local QA scenario drafts. Run it only on files you intend to process, choose output paths carefully, avoid sensitive input unless needed, and re-review the script if you modify resources/spec.json to enable one of the dormant audit modes.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill declares no permissions, yet its content explicitly references local resource reads and a possible `python3` shell invocation that can write output files. This creates a capability/permission mismatch that can mislead reviewers and downstream policy enforcement, increasing the risk of unintended file access or command execution when the skill is invoked.

Description-Behavior Mismatch

High

• Confidence: 96% confidence
• Finding: The script supports multiple audit modes including directory, CSV, pattern, and skill-package auditing that materially exceed the declared purpose of QA scenario synthesis. This capability expansion increases the attack surface and can enable unintended repository inspection or security-review behavior under a misleading skill identity, which is dangerous in agent environments that rely on metadata and scope for trust decisions.

Context-Inappropriate Capability

High

• Confidence: 97% confidence
• Finding: The built-in regex scanner looks for secrets, internal URLs, and shell-execution patterns, which is security-analysis functionality unrelated to the stated QA scenario synthesis task. In a mismatched skill, this is risky because it can scan arbitrary files and surface sensitive snippets from local content, creating data exposure and capability deception concerns.

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The skill-package audit checks repository structure and parses SKILL.md frontmatter, which is unrelated to generating QA scenarios. While not immediately code-executing, it allows the tool to inspect package internals and metadata under a misleading purpose, undermining user expectations and enabling unauthorized inventorying of local project contents.

VirusTotal

66/66 vendors flagged this skill as clean.