ClawHub
Back to skill

Security audit

Continuous Field Computation

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for structuring task complexity and response detail, with no evidence of hidden code, credential access, or data movement.

Install this if you want a meta-skill that changes how the agent structures complex work. Be aware that broad phrases like semantic density or transparency control may activate it in conversations where you only meant to discuss those ideas, so use explicit invocation or disable it if that becomes distracting.

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
90% confidence
Finding
The trigger phrases are broad and loosely bounded, which can cause accidental activation in unrelated conversations. In a meta-skill that adapts processing depth and may alter how tasks are handled, ambiguous invocation increases the risk of prompt confusion, unintended policy application, and user requests being routed through the wrong behavior profile.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.