Back to skill

Security audit

Math & Statistics Graphing Engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward math graphing integration that sends requested math or data to an external graphing MCP service and returns shareable interactive graph URLs.

Install this if you are comfortable using Mathtalking's external MCP service for graphing. Avoid sending confidential datasets, private student records, proprietary formulas, or sensitive analysis unless you are comfortable with them being processed externally and exposed through a shareable interactive URL.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs the agent to always share an interactive URL hosted on an external service, but the description does not warn users that outputs are externally hosted and shareable. This can cause unintended disclosure of sensitive user-provided data, formulas, datasets, or analysis results to a third-party service, especially in educational or analytical contexts where users may paste private data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.