ClawHub
Back to skill

Security audit

rigorous-reasoning

Security checks across malware telemetry and agentic risk

Overview

This is a reasoning-style skill that changes how the agent evaluates claims, with no files, credentials, network access, or execution behavior beyond markdown instructions.

Install this if you want the agent to be more direct and less agreeable during analysis, debate, or conflict evaluation. Be aware that the broad triggers may make the agent adopt this stricter reasoning posture in ordinary analysis conversations too.

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
83% confidence
Finding
The trigger list includes very broad, common terms like "analysis," "debate," and "critical-thinking," which can cause the skill to activate in many unrelated conversations. Unintended activation can override normal agent behavior and inject this skill’s strong reasoning posture into contexts where it was not requested, creating prompt-routing risk and potentially interfering with safer or more task-appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.