Back to skill

Security audit

Break-Even Analysis

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill has limited local access, but its incomplete calculator should not be relied on for business decisions.

Do not treat successful report generation as completed analysis: independently calculate and verify the results until the script and template are corrected. Use a dedicated output folder because calculation.md is overwritten. The optional unsigned Windows app is unnecessary for this workflow and requires separate evaluation.

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
  • 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 script assigns the financial formulas to a string and prints that string in calculation.md; it never evaluates them. Its primary behavior is input transcription and report generation rather than the declared break-even calculation. Local input reading and output writing are supporting implementation details, and no unrelated resource access or undeclared external activity is evident.

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 skill reports inputs and a formula string instead of computing the promised break-even results.

Medium
Category
Excessive Agency
Confidence
100% confidence
Finding

The script parses inputs and writes a calculation report containing a formula string, but never computes contribution margin, break-even units, break-even revenue, or headroom. This is a functional-integrity failure rather than a code-execution vulnerability: users or downstream agents may mistake successful report generation for completed financial analysis. The financial decision-making context increases the consequences of relying on the incomplete output, although there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.