ClawHub
Back to skill

Security audit

yaoshunyu-perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only governance perspective skill with no hidden execution or data access; the only notable issue is minor tone/language guidance in a reference file.

Before installing, understand that this skill is an opinionated Chinese-language governance/persona aid for skill review workflows, not a general coding helper. It should be used for the stated penguin-oss-suite review gates, and users should still prefer their own language or host locale if that conflicts with the style note.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly states a language preference ('In Chinese, sound soft and companion-like') that can steer agent behavior regardless of the user's chosen language. This is a real policy/UX control issue because it can override user intent or host application expectations, though it is not a code-execution or data-exfiltration risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.