ClawHub
Back to skill

Security audit

gary-namie-workplace-bullying-institute

Security checks for vulnerabilities and agentic risk

Overview

This is a static workplace-bullying guidance skill with no code execution, credentials, persistence, or hidden system changes, though some triggers are broad and may activate in unrelated conversations.

Install only if you want a Chinese-language reference skill for WBI-style workplace bullying analysis. Be aware that broad triggers, especially '纳米', could invoke it for unrelated topics; narrowing those triggers would improve fit.

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)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The natural-language instructions and descriptions are entirely in Chinese, which can amount to forcing a specific language without user opt-in. The file does not indicate that the skill is region-specific or that users may choose another language.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list includes broad, generic phrases such as “WBI”, “反霸凌政策”, “霸凌个案”, and especially “目标应对”, which can match many unrelated user requests and cause unintended invocation. In a workplace-advice skill, accidental activation can inject a narrow ideological framework into sensitive HR or legal discussions, potentially misleading users or displacing more appropriate guidance.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding
The trigger “纳米” is extremely short and polysemous, likely to appear in unrelated conversations about nanotechnology, materials science, measurement units, or names. This can cause frequent false activations, and in sensitive workplace contexts may insert irrelevant bullying guidance into unrelated user sessions.

Static analysis

No suspicious patterns detected.