ClawHub
Back to skill

Security audit

Evolutionary Iteration

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed planning method for generating and selecting solution options, with no executable code or hidden data access.

Install only if you want the agent to apply a structured solution-generation and selection workflow. Because a few trigger phrases are generic, review when it activates and disable it if it appears during unrelated planning tasks.

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 list contains broad, generic phrases such as '迭代循环' and '最优选择' without scope limits, increasing the chance the skill activates for unrelated user requests. In an agent setting, over-broad activation can cause unintended routing, inappropriate instruction injection into unrelated tasks, and expansion of the skill’s influence beyond its intended domain.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.