Back to plugin

Security audit

WayID

Security checks across malware telemetry and agentic risk

Overview

The plugin is purpose-aligned, but it saves a persistent private signing key on disk and can trigger on broad identity questions.

Install only if you are comfortable with this plugin creating and reusing a local signing private key for your agent identity, contacting the WayID issuer to claim and display identity information, and answering broad identity questions from WayID certificate output. Treat the workspace key file as sensitive and prefer explicit slash commands when you want identity display.

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 manifest description includes broad trigger phrases such as 'who you are, who owns you, who you belong to, or any variant of identity/ownership/provenance question,' which can cause the skill to activate on a wide range of normal user queries. Because the skill instructs the agent to return tool output character-for-character and not answer from its own knowledge, overbroad activation can unnecessarily route benign identity-related conversations through an external identity service and suppress safer contextual handling.

VirusTotal

60/60 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.