ClawHub
Back to skill

Security audit

Calculator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple calculator instruction-only skill with no code, network access, persistence, or sensitive data handling.

This skill is appropriate to install if you want a basic arithmetic helper. The main practical caveat is that it may be invoked for broadly worded math requests, but it does not introduce executable code or special access.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill description uses broad trigger phrases such as "calculate," "compute," and "do math," which can match many ordinary requests beyond the intended narrow calculator use case. Overly broad activation can cause unintended invocation, misrouting user requests, and increasing the chance that this skill handles prompts it was not meant to process.

Static analysis

No suspicious patterns detected.