Sec Audit Cn

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is a security-audit guidance skill with broad activation keywords, but no evidence of hidden execution, persistence, data theft, or destructive behavior.

Install this if you want a security-review assistant for code and configuration work. Be aware that its activation keywords are broad, so it may appear in some general security conversations; use it deliberately and avoid pasting real secrets unless you intentionally want them reviewed in your local agent context.

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 (2)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list contains broad security-related terms that can cause the skill to activate in contexts the user did not explicitly intend. In a security-audit skill, over-triggering is risky because it may inject region-specific or security-review behavior into unrelated conversations, creating prompt-routing confusion and increasing exposure to adversarial prompt abuse.

Vague Triggers

Low

• Confidence: 84% confidence
• Finding: Additional trigger terms are also broad and ambiguous, which increases the chance of unintended invocation. While this is less severe than direct code execution, misrouting to a security-specialist skill can alter system behavior, produce irrelevant output, or widen the attack surface for prompt-injection attempts.

VirusTotal

65/65 vendors flagged this skill as clean.