ClawHub
Back to skill

Security audit

balltalk

Security checks for vulnerabilities and agentic risk

Overview

This is a basketball advice skill that asks the agent to use current web data for stats and fantasy guidance, with no executable code or hidden high-impact behavior found.

Before installing, expect the skill to activate for many basketball or NBA questions and to use web search for current stats and fantasy context. It does not include executable code or ask for private accounts, credentials, or local data 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/banner.svg (reported line 17)May include surrounding context.

text
<rect width="1280" height="640" fill="url(#bg)"/>

  <!-- Ambient glow -->
  <circle cx="320" cy="320" r="250" fill="#e85d04" opacity="0.04"/>
  <circle cx="320" cy="320" r="150" fill="#e85d04" opacity="0.03"/>
  <circle cx="960" cy="320" r="250" fill="#c2185b" opacity="0.03"/>

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/banner.svg (reported line 45)May include surrounding context.

text
<!-- "talk" -->
  <text x="640" y="540" text-anchor="middle" font-family="system-ui, -apple-system, 'Segoe UI', Helvetica, Arial, sans-serif" font-size="100" font-weight="300" letter-spacing="3" fill="#ffffff" opacity="0.7">talk</text>

  <!-- Tagline -->
  <text x="640" y="600" text-anchor="middle" font-family="system-ui, -apple-system, 'Segoe UI', Helvetica, Arial, sans-serif" font-size="18" font-weight="400" fill="#ffffff" opacity="0.3" letter-spacing="4">YOUR AI BASKETBALL BRAIN</text>

  <!-- Corner brackets -->

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest includes broad trigger phrases such as 'basketball', 'NBA', and generic comparative or fantasy prompts that can cause the skill to activate in many loosely related contexts. Overbroad activation increases the chance of unintended routing, which can override more appropriate skills, cause unnecessary web access, or expose users to responses shaped by this skill when they did not explicitly request it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.