Back to skill

Security audit

Payroll

Security checks for vulnerabilities and agentic risk

Overview

This is a payroll guidance skill with broad activation terms, but its behavior is disclosed, text-only, and aligned with helping small businesses handle payroll tasks.

Before installing, understand that this skill may be invoked by common payroll terms and may ask for sensitive employee or tax details. Use it for guidance and calculations, but verify jurisdiction-specific payroll, tax, and legal obligations with official sources or a qualified professional before acting.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list contains broad natural-language phrases such as "payroll," "W-2," and "pay employees" that are likely to appear in ordinary business conversations. This can cause unintended skill activation and route sensitive payroll or HR discussions into this skill when the user did not explicitly intend to invoke it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is very broad and lacks clear activation boundaries, so an agent may invoke it for a wide range of loosely related business, HR, tax, or compliance questions. That increases the chance of inappropriate routing and over-trust in the skill’s guidance for regulated payroll matters, where jurisdiction-specific mistakes can create legal and financial harm.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The phrase "Anyone who has received a payroll tax notice and needs to understand it" is broad and, alongside the general trigger design, suggests wide applicability without explicit activation constraints. In a manifest, lack of specificity about when the skill should or should not activate increases the risk of unintended matching.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.