Back to skill

Security audit

helpdesk

Security checks for vulnerabilities and agentic risk

Overview

The skill appears intended for helpdesk ticketing, but its instructions are too broad and reference credentialed ticket operations through a missing script without clear data-handling safeguards.

Review this skill before installing. Confirm what script will actually run, what helpdesk system it contacts, what ticket actions it can perform, and how the TICKET_API_KEY and user-provided support content are protected. Avoid using it with confidential or regulated data until those boundaries are documented.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 documented 'When to Use' conditions are very broad and generic, which can cause an agent to invoke this skill for loosely related support or communication tasks without clear scope boundaries. In a helpdesk context, that increases the chance of unnecessary ticket actions or unintended transmission of user data to an external system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation instructs use of an API key and implies sending input to a helpdesk system, but it does not warn that user-provided content may be transmitted to an external service or that credentials are required and sensitive. This can lead to accidental disclosure of confidential data, mishandling of secrets, or use of the skill without informed consent.

Content

No source excerpt is available for this finding.