ClawHub
Back to skill

Security audit

Coin Identifier

Security checks for vulnerabilities and agentic risk

Overview

This coin-identification skill is coherent and limited: it analyzes user-provided coin photos and only stores local notes if the user approves.

Before installing, decide whether you want this skill to save local coin-identification notes and whether it should activate proactively or only when you explicitly ask. Avoid saving unrelated personal information in its local memory.

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
93% confidence
Finding
The setup instructions explicitly ask to broaden and clarify future activation, including whether the skill should activate whenever coins, mint marks, or unidentified collection pieces are mentioned and whether it should jump in proactively. This creates an overly broad trigger surface that can cause the skill to engage outside clear user intent, increasing the chance of unwanted data collection, inappropriate persistence, or interference with unrelated conversations.

Static analysis

No suspicious patterns detected.