ClawHub
Back to skill

Security audit

Amazon Product to Video Script

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Amazon listing and review analysis helper for producing marketing video scripts, with only a minor routing concern from one broad trigger phrase.

Installers should expect the agent to browse Amazon product pages and read public listing and embedded review text. Avoid using it for non-Amazon products unless you explicitly provide Amazon listing context; the broad trigger should ideally be tightened in a future version.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger text is intentionally broad enough to activate on common writing-help requests like asking what kind of video would work or to write a video script. That can cause the skill to take over in situations where the user did not clearly request Amazon-product analysis, increasing the chance of inappropriate tool use, unexpected browsing, and context hijacking from more relevant skills.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase "write a video script for this product" is broad and not constrained to Amazon links or short-form marketing use cases. This can cause the skill to activate on generic product-script requests outside its intended scope, leading to misrouting, unexpected handling of user requests, and possible bypass of more appropriate skills or safety logic tied to narrower routing.

Static analysis

No suspicious patterns detected.