role-configurator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed role setup helper that can change the local SOUL.md assistant configuration file, so users should review the generated role before applying it.

Install this only if you want a skill that may update your OpenClaw SOUL.md role file. Before applying a generated role, check the exact workspace path, review the full file content, keep the backup, and treat the mental-health and finance presets as general support or education rather than professional advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README advertises one-click generation that automatically writes to SOUL.md, but provides no warning, consent language, or description of what will be modified. In a role-configuration skill, writing to a core assistant configuration file can materially change agent behavior, so undocumented file modification increases the risk of unintended or socially engineered persistence.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The quick-trigger phrases are broad enough to activate during ordinary conversation, which can cause the wrong skill to take control of a user interaction. In this skill, accidental activation is more dangerous because the workflow leads toward collecting preferences and potentially writing configuration files.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger-word section contains generic phrases like setup, recommend a role, or switch roles that may match unrelated user requests. Because this is an installation/setup skill with persistence behavior, ambiguous routing increases the chance of unauthorized or confusing configuration changes.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill states it will automatically generate and write a role config file but does not clearly warn the user about filesystem modification, target path, or overwrite behavior. In a first-run setup skill, this can lead to silent persistence, accidental overwrites, or abuse if the write destination is broader than intended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The template presents a 'Mental Health Companion' as providing emotional support, mindfulness guidance, and coping strategies without any boundary-setting, crisis disclaimer, or instruction to seek qualified help for serious mental health concerns. In a role-configurator skill, this can normalize the assistant as a substitute for professional care and increase the risk of unsafe reliance during vulnerable moments.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The 'Financial Advisor' template frames the assistant as a personal finance guide covering budgeting, saving, investing, and debt management, but does not disclose limitations or warn users against treating outputs as professional financial advice. Because this is a preset role intended for easy adoption, users may over-trust recommendations that materially affect their finances.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal