ClawHub
Back to skill

Security audit

Nm Imbue Rigorous Reasoning

Security checks across malware telemetry and agentic risk

Overview

This is a text-only reasoning skill that changes conversational style but does not add code execution, data access, persistence, or hidden external behavior.

Install this if you want the agent to be more direct, evidence-focused, and resistant to agreeable hedging. Be aware that broad triggers like "analysis" may make the style appear in more conversations than expected, and use caution for sensitive personal, crisis, medical, legal, or abuse-related situations where empathy and safety policies must remain primary.

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
92% confidence
Finding
The trigger phrase 'analysis' is extremely broad and likely to match many ordinary user requests, causing this skill to activate outside its intended niche. That can inappropriately bias agent behavior toward a rigid anti-sycophancy posture in unrelated contexts, increasing prompt-surface interference and making downstream behavior less predictable.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrase 'debate' is underspecified and broad enough to activate on many harmless conversations, not just the contested reasoning scenarios this skill targets. Unnecessary activation can override normal conversational controls and introduce unintended behavioral steering, especially because the skill contains strong priority and override language.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill is triggered by broad topics like disagreements, ethical questions, and contested claims, which are common in normal conversations. That makes unintended activation plausible, and because the protocol strongly instructs the agent to discount emotional context, speculative risk, and social pushback, it could inappropriately steer responses in sensitive situations such as harassment, abuse, safety, or mental-health-adjacent conflicts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal