ClawHub
Back to skill

Security audit

Management

Security checks for vulnerabilities and agentic risk

Overview

This is a plain management guidance skill with no code, tools, credential access, persistence, or hidden execution behavior.

Install only if you want broad management, leadership, academic, and HR-adjacent coaching. Treat its advice on discipline, termination, harassment, accommodations, discrimination, and investigations as support for preparation, not as a substitute for HR or legal review.

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
92% confidence
Finding

This markdown skill file names the skill broadly as "Management" and describes it generally as covering management principles, team leadership, and organizational effectiveness, but it does not define explicit trigger phrases, contexts, or exclusion conditions. That broad natural-language scope could overlap with many common conversations and make it unclear when the skill should activate versus when it should not.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.