Back to skill

Security audit

DCL Sentinel Trace — PII Redactor & Identity Exposure Detector

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent PII-checking checklist with an optional disclosed paid MCP scan, and I found no hidden execution, persistence, or destructive behavior.

Use the free checklist for local-only review. Use the live MCP mode only when you are comfortable sending the text being scanned to Fronesis Labs and paying the per-call USDC fee for an on-chain verification record.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.