gate-info-riskcheck

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

Overview

This is a read-only crypto risk-check skill that clearly discloses its main limitation: address safety checks only provide basic on-chain information for now.

Install this if you want read-only Gate-Info token and contract risk reports. Treat address results as basic on-chain information, not a blacklist, compliance, or definitive safety verdict, until the missing address-risk capability is actually available.

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: 91% confidence
• Finding: The trigger examples are overly broad and can match common user phrasing outside the narrowly intended scope, increasing the chance this skill activates when the user actually needs a broader research workflow. In this context, misrouting is security-relevant because users may receive incomplete risk analysis or bypass the intended multi-dimension skill-selection boundary described in the metadata.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The address-check triggers are ambiguous and especially the phrase about a 'blacklisted address' implies compliance/risk capabilities that the scenario later says are not actually available. This can cause unsafe over-triggering, user confusion, and reliance on incomplete address information for compliance-style decisions.

VirusTotal

66/66 vendors flagged this skill as clean.