ClawHub
Back to skill

Security audit

Three-Radius Model — 认知/能力/行动三半径

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable coaching skill for diagnosing performance gaps, with no hidden code, credential access, or external data handling found.

Safe to install for coaching and post-mortem style analysis. Review any generated diagnostic before sharing it, and do not allow the agent to persist real user or team failure examples into reusable notes unless you intentionally approve that behavior.

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

Low
Confidence
88% confidence
Finding
The heading includes Chinese text ("认知/能力/行动三半径") even though the file does not state that the skill is bilingual, region-specific, or that users may choose their preferred language. This can violate language/locale policy because it introduces a specific language without documented opt-in or clear necessity.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.