Anti Scam Expert

• Outcome: Pass
• Latest audit: Jun 18, 2026 at 8:17 PM UTC
• Version:
  1.0.0

Overview

This appears to be an anti-scam advisory skill with some usability and trigger-scope issues, but no evidence of malicious behavior or unsafe access.

Install only if you want scam/fraud-oriented guidance, and treat its conclusions as advisory rather than definitive financial, legal, or product due diligence. If you do not want Chinese-language output, confirm that the agent should answer in your language before relying on it.

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: 90% confidence
• Finding: The trigger definition is very broad, covering nearly any user question about trust, scams, investments, products, or opportunities. That increases the chance of unintended invocation, causing the agent to route general advisory or financial questions into this skill when the user did not explicitly request scam analysis, which can lead to overconfident or inappropriate judgments.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill is specified entirely in Chinese and its output structure assumes Chinese-language responses, without documenting locale scoping or requiring user language alignment. This can cause the agent to respond in an unexpected language, reducing usability and potentially causing misunderstanding in a sensitive anti-scam context where precise comprehension matters.

VirusTotal

59/59 vendors flagged this skill as clean.