ClawHub
Back to skill

Security audit

agent-runtime-impact-research

Security checks across malware telemetry and agentic risk

Overview

This is a transparent research-writing skill for analyzing agent runtime releases, with only ordinary web research expected and no hidden local access or persistence.

Before installing, note that this skill is intended for structured impact research on agent runtime releases and expects current web/source searches. It will tend to answer in concise Chinese unless you tell the agent to use another language.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The writing rules state "Use concise Chinese," which enforces a specific language for outputs. This is a natural-language policy concern because the file does not indicate that the user can choose the output language or opt into Chinese-only responses.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.