Skylv Consensus Persona Engine

Security checks across malware telemetry and agentic risk

Overview

This is a small local tool for voting on AI persona settings, with no evidence of hidden network access, credential use, or destructive behavior beyond its disclosed local vote file reset.

Install if you want a local helper for persona consensus. Review generated rules before applying them to real agents, especially autonomy-related rules, and run it only in a directory where creating or deleting .consensus_votes.json is acceptable.

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
93% confidence
Finding
The trigger phrase "consensus persona engine" is fairly generic and overlaps with ordinary user requests about personas, consensus, or multi-agent behavior. An underspecified trigger can cause the skill to activate unintentionally in unrelated contexts, which may alter agent behavior or inject this skill's workflow when the user did not request it.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal