Back to skill

Security audit

Break-Even Analysis

Security checks for vulnerabilities and agentic risk

Overview

The bundled workflow has limited, disclosed access, but its calculator does not perform the promised calculations.

Use an independently verified calculator for actual results: this helper performs no calculations and can silently report supplied costs as zero. Choose a dedicated output folder to avoid replacing an existing report. The optional Windows application is unnecessary for the Python workflow and is outside this assessment.

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
100% confidence
Finding

The script's primary behavior is report generation rather than the declared financial calculation. FORMULA is merely appended to the output as text and is never evaluated or implemented with arithmetic. Consequently, the report contains no break-even, contribution-margin, or sensitivity results. Local input reading and report writing are supporting implementation details, not separate mismatches.

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 claims to compute break-even results and checks, but only writes inputs and formula text to a report.

Medium
Category
Excessive Agency
Confidence
100% confidence
Finding

The script parses and reports input values but never evaluates the formula or performs the advertised margin and sensitivity checks. This is an output-integrity defect rather than a code-execution vulnerability: a user or downstream agent could mistake successful execution and the generated report for completed financial analysis, leading to unsupported pricing or investment decisions. The financial context increases the consequences, although the report's lack of calculated results is visible and its disclaimers provide some mitigation.

Content

No source excerpt is available for this finding.