ClawHub
Back to skill

Security audit

Math Evaluate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple API-backed math helper that clearly discloses sending math inputs to an external service.

Install only if you are comfortable sending math expressions, variables, and datasets to the listed external service. Do not use it for proprietary formulas, confidential business metrics, personal data, or regulated data unless you independently accept the service's privacy and retention claims.

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
  • 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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to send user-supplied math expressions and variables to an external third-party API. Even if the content appears low sensitivity, this creates a real data-exfiltration path because users may include proprietary formulas, business metrics, or other sensitive values in expressions, and the skill advertises no strong technical guarantees beyond a claim that the service does not retain logs.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

Evaluate Expression

bash
curl -X POST https://math.agentutil.net/v1/evaluate \
  -H "Content-Type: application/json" \
  -d '{"expression": "2 * x + y", "variables": {"x": 20, "y": 2}}'

Static analysis

No suspicious patterns detected.