ClawHub
Back to skill

Security audit

payroll-cost-calculator

Security checks for vulnerabilities and agentic risk

Overview

The calculator can produce materially misleading payroll estimates because its calculations and accepted input format contradict its instructions.

Wait for a corrected version before relying on its payroll totals. The documented input can yield zero estimates, and CSV input still receives incomplete tax calculations. Have payroll estimates independently checked. The optional Windows application is unnecessary for the calculator and requires a separate trust decision.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The implementation behavior reported by static analysis contradicts the promised itemized payroll calculation: applying a flat tax to all costs while omitting separate components can produce materially incorrect employer-cost estimates. That undermines financial output integrity and could mislead hiring and budgeting decisions, although the estimate-only guardrails reduce the risk of direct tax-filing harm. The script was not supplied, so this assessment relies on the reported implementation behavior rather than independent code verification.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The employer-cost calculator only sums supplied amounts and adds a flat 7.65% tax, rather than calculating the payroll components promised by the manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script adds a flat 7.65% to every supplied amount without distinguishing taxable wages from benefits or calculating FUTA, workers’ compensation, wage-base limits, or other promised components. In an employer-cost calculator, this mismatch can produce materially misleading hiring budgets; the estimate disclaimer reduces reliance risk but does not correct the calculation or clearly disclose its omissions. This is a financial-output integrity issue, not evidence of malicious execution or data theft.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.