ClawHub
Back to skill

Security audit

christine-porath-civility-at-work

Security checks for vulnerabilities and agentic risk

Overview

This is a simple workplace-civility reference skill with no code execution, data access, persistence, or hidden behavior.

Before installing, consider whether you want a broad Chinese-language workplace civility reference skill that may activate on generic discussions of rudeness; there is no evidence of code execution, data access, persistence, or exfiltration in the artifact.

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
  • 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 (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list contains broad, common terms such as “无礼”, “粗鲁”, and “职场文明” that can match ordinary user phrasing outside a narrow request for this specific framework. This can cause unintended skill activation, leading the agent to inject irrelevant guidance or route conversations incorrectly, though it does not by itself enable code execution or direct data compromise.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding
The single trigger “无礼” is a short, generic term that can appear in many unrelated conversations. Because the skill is advisory and domain-specific, broad matching increases the chance of accidental invocation and context hijacking, especially in multilingual or loosely matched routing systems.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
89% confidence
Finding
The trigger “粗鲁” is similarly too short and generic, making unintended activation likely when users discuss rudeness in non-workplace contexts. In an agent system, this can degrade reliability by selecting this skill when another skill or no skill would be more appropriate.

Static analysis

No suspicious patterns detected.