Back to skill

Security audit

Hello World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting skill with minor usability mismatch, not a security threat.

Before installing, understand that this skill may answer simple greetings with only `Hello World`; do not expect localization or a conversational follow-up.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The metadata and description suggest a custom localized greeting, but the skill always emits the fixed English string 'Hello World' with no user choice. This mismatch can cause misleading behavior, override localization expectations, and reduce trust or usability, though it is not a direct security compromise on its own.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are broad enough to match common conversational openers like 'hello' or 'hi', which creates a high likelihood of accidental invocation during normal user requests. Because the skill also instructs the agent to terminate further execution and return a fixed response, it can preempt legitimate multi-intent interactions and degrade expected behavior.

Content

No source excerpt is available for this finding.