ClawHub
Back to skill

Security audit

Agent Self-Introduction Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk self-introduction writing skill with no code, tools, persistence, credential use, or data access.

Installers should treat this as a persona and introduction helper, not an identity, authentication, or memory system. Consider narrowing when it activates if you only want it used on explicit self-introduction or onboarding requests.

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
Confidence
93% confidence
Finding
The 'When to Use This Skill' section describes general situations like introducing itself, clarifying tone, or presenting identity across sessions, but it does not define concrete trigger phrases, scope limits, or negative examples. Because this is a markdown file, these broad activation conditions could lead to unintended invocation in many ordinary conversational contexts.

Static analysis

No suspicious patterns detected.