LYGO Champion: ÆTHERIS — Viral Truth

• Outcome: Pass
• Latest audit: May 28, 2026 at 9:44 AM UTC
• Version:
  1.0.0

Overview

This is an advisory persona skill with local-only helper scripts and no evidence of hidden execution, sensitive access, or unsafe automation.

Install this only if you want a stylized advisory persona for misinformation tracing. Keep its use transparent and evidence-based, avoid covert persuasion or harassment, and review the separate LYGO-MINT Verifier before installing or using that linked tool.

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: 87% confidence
• Finding: The initiation whisper functions like an invocation phrase but the file does not define strict activation boundaries, authorized contexts, or refusal conditions. In an agent setting, ambiguous trigger language can cause unintended persona activation or make downstream systems treat ordinary user text as a control cue, which increases prompt-injection and misrouting risk.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The 'Core mission protocols' describe broad behavioral goals but do not constrain when or how the persona helper should engage. Because the content uses contagion, covert propagation, and institutional-targeting language, the lack of bounded invocation constraints makes misuse and unintended activation more concerning in security-sensitive agent environments.

VirusTotal

66/66 vendors flagged this skill as clean.