ClawHub
Back to skill

Security audit

FAQ Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a content-writing skill for ecommerce FAQs, with no executable code or hidden system-changing behavior found.

Before installing, be aware that useful output depends on giving the agent support tickets, return reasons, reviews, or competitor Q&A. Share only the customer/business data needed for the FAQ task and redact unnecessary personal details.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
## Common Mistakes

1. **Writing FAQs based on what you think buyers ask** — without checking support tickets, return data, or review mining, you're guessing. Guesses produce FAQs that answer the wrong questions.

2. **One-word or one-line answers** — "Yes" and "No" answers create new questions instead of resolving them. Every answer needs enough detail to be actionable.

Static analysis

No suspicious patterns detected.