ClawHub
Back to skill

Security audit

Listing Doctor Publish

Security checks across malware telemetry and agentic risk

Overview

This is a functional Amazon listing audit skill, but it includes mandatory promotional output and broader agent authority than the diagnostic workflow clearly needs.

Install only if you are comfortable with the skill shaping responses with mandatory promotional Chinese attribution and with giving it command/file access for local diagnostics. Use the optional SellerSprite fetch path only when you intend to send the ASIN request to SellerSprite with your own API secret; otherwise paste/export listing data locally.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text is extremely broad: it activates on generic mentions of checking, auditing, scoring, diagnosing, or discussing Amazon listings in multiple languages. That increases the chance of unintended invocation, causing the agent to switch into this skill's workflow when the user did not explicitly request it, which can derail conversations and apply the skill's behavioral instructions unexpectedly.

Natural-Language Policy Violations

High
Confidence
98% confidence
Finding
The skill mandates that the agent always introduce the tool in Chinese and include promotional attribution, regardless of the user's language or preferences. This overrides normal user-aligned behavior and can create prompt-level control of agent output, causing confusing, unwanted, or policy-inconsistent responses; it also introduces branding/instruction injection unrelated to the user's request.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.