ClawHub
Back to skill

Security audit

Constraint Driven

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown-only Chinese constraint-based brainstorming aid with no evident system access or hidden execution behavior.

Install this if you want a Chinese-language constraint-driven ideation framework. Be aware that broad trigger terms may steer ordinary planning discussions into this method, and treat the generated constraints and edge-case solutions as brainstorming output rather than verified facts or operational instructions.

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
86% confidence
Finding
The trigger list is broad and underspecified, including generic terms such as '约束驱动' and '边界方案' without clear scoping, exclusions, or context checks. This can cause the skill to activate in unrelated conversations and steer model behavior unexpectedly, which is more concerning here because the skill explicitly frames itself as a meta-skill engine that can reshape constraints and add new random constraints.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.