ClawHub
Back to skill

Security audit

Reasoning Personas

Security checks across malware telemetry and agentic risk

Overview

This skill only adds disclosed reasoning-persona prompts and does not include code, data access, persistence, or external connections.

Install this if you want the assistant to use stronger persona-based reasoning during brainstorming, reviews, and decisions. Be aware it may make answers more contrarian, critical, or precedent-focused without always labeling the active mode; ask the assistant to label personas or stay neutral for sensitive conversations.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to match very common requests such as brainstorming, reviewing plans, and decision-making, which can cause it to activate in many unrelated conversations. Over-broad activation increases the chance that behavioral instructions from the skill override or steer the assistant in contexts where the user did not explicitly ask for this mode, expanding the skill's effective authority.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The auto-activation map uses ambiguous labels such as brainstorming, code-review, and exploring new ideas without clear boundaries, making automatic activation unpredictable and overly permissive. In practice this can let the skill silently influence responses across many normal tasks, which is risky because it changes reasoning behavior without explicit user consent or tight scope control.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.