ClawHub
Back to skill

Security audit

Cb User Persona Builder

Security checks across malware telemetry and agentic risk

Overview

This is a text-only persona-building skill with no code execution, credential access, persistence, or hidden high-impact behavior.

Safe to install for structured market-persona drafting. Treat its personas as hypotheses, verify cultural claims with real research, and avoid providing confidential customer data unless you are comfortable sharing it with your agent.

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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The suggested trigger "Help me build user personas for [product] in [market]" and the fallback "Or just describe your target market and what you sell" are very broad natural-language activation examples. The file does not define boundaries or negative examples, so the skill could be invoked by ordinary market-research requests that may not clearly intend this specific skill.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The file introduces a full usage scenario in Chinese, but there is no accompanying statement that the skill supports multiple languages by user choice or that locale follows user input. This can be read as an undocumented language/locale behavior rather than an explicit opt-in language policy.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The manifest sets `"language": "en"`, which imposes a specific language/locale choice in natural-language metadata. Under the policy criteria, locale restrictions should either be optional for the user or clearly justified as region-specific; neither is present here.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.