Back to skill

Security audit

Hello World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting skill with no executable code, persistence, data access, or external communication.

This skill is safe to install for a simple greeting test. Be aware it may activate for ordinary greetings or short friendly-reply requests, so tighten the description if predictable routing among many skills matters.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares very broad trigger conditions such as 'says hello/hi' and 'wants a friendly short reply,' which overlap with common conversational behavior. This can cause unintended invocation or priority conflicts with other skills, making routing less predictable even though the skill itself is harmless.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The response rules hardcode English output for several common greetings and only partially localize some Chinese variants, without adapting to the user's language choice. This is primarily a quality and UX issue, but in multi-skill environments it can also create inappropriate or unexpected behavior for non-English users.

Content

No source excerpt is available for this finding.