Back to skill

Security audit

Duanzj Hello Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting demo skill with no evidence of hidden access, persistence, network use, or destructive behavior.

Safe to install as a basic test or learning skill. Be aware it may activate on generic greeting requests, but the inspected behavior is limited to returning hello-world style responses.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger examples are broad, common phrases such as '打个招呼' and '问个好', which can overlap with normal conversation and cause the skill to activate when the user did not explicitly intend to invoke it. In this specific skill, the behavior is harmless because it only returns a greeting, but the pattern is still a real invocation-scope weakness that could lead to misrouting or unexpected execution.

Content

No source excerpt is available for this finding.