ClawHub
Back to skill

Security audit

LYGO Champion: sraith shadow sentinel

Security checks across malware telemetry and agentic risk

Overview

This is a small deprecated persona helper with only local self-check/hash scripts and disclosed references to a separate verifier tool.

Install this as a persona/helper skill, not as an automation tool. Be deliberate before following the linked verifier instructions, especially minting or backfilling anchors, because those actions belong to a separate workflow that may write verification records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation phrases are overly broad natural-language requests like “Mint this Champion pack” and “Show the hash + anchor snippet,” without explicit gating, scope checks, or confirmation requirements. In an agent setting, this can cause unintended invocation on attacker-supplied content or file paths, leading the skill to process untrusted inputs and potentially publish or backfill anchors for the wrong material.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.