ClawHub
Back to skill

Security audit

Zhuyuanzhang Think Partner

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only historical leadership thinking framework with clear boundaries against using it for punishment, legal, HR, or other professional decisions.

Install this as a historical strategy and reflection aid, not as an authority for personnel actions, legal/compliance decisions, safety matters, finance, medical, or mental-health advice. Be especially careful with workplace conflict prompts: use it to structure questions and tradeoffs, then rely on your organization’s formal process and qualified professionals for decisions affecting people.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation section uses broad prompts such as starting an organization, handling scarce resources, managing betrayal, or balancing leadership and execution, without strong exclusion criteria or tighter routing boundaries. This can cause the skill to activate in sensitive contexts like employment, disciplinary, legal, or high-stakes organizational decisions, where its 'iron hand' framing may shape advice even though later disclaimers try to limit direct use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.