ClawHub
Back to skill

Security audit

terms-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides guidance for creating a Terms of Service page and does not request access to files, accounts, credentials, tools, or background execution.

This appears safe to install for drafting or improving Terms of Service pages. Treat its output as drafting help, not legal advice, and have a qualified lawyer review terms for the relevant product, jurisdiction, and user base.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The phrase "When the user wants to create, optimize, or structure Terms of Service page" is broad and does not clearly bound when this skill should activate versus other legal-writing or page-generation skills. While examples are provided, the description lacks negative examples or explicit exclusion criteria beyond one related skill, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.