AI幻觉检测专家

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 11:53 AM UTC
• Version:
  1.0.0

Overview

This is a local hallucination-checking skill with no executable files, credentials, or hidden data handling found.

Installers should expect this skill to analyze text they deliberately provide for fact-checking. Avoid sending sensitive documents unless you are comfortable with local model processing and any first-run model download behavior in your agent environment.

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: 89% confidence
• Finding: The skill advertises a very broad trigger for checking 'any AI-generated content' without clear scoping, explicit invocation boundaries, or user confirmation. In an agent environment, this can cause over-activation, unintended interception of unrelated prompts, or prompt-routing confusion, which may interfere with normal agent behavior and expand the skill’s access to sensitive user content beyond what is necessary.

VirusTotal

64/64 vendors flagged this skill as clean.