ClawHub
Back to skill

Security audit

Review Request Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a markdown-only review outreach planner, but its negative-feedback routing can encourage review gating or suppression of unhappy-customer reviews.

Install only if you are prepared to tighten the workflow: offer support neutrally to all buyers without delaying or diverting reviews, verify opt-in and suppression rules before SMS/WhatsApp/email outreach, and ensure QR or redirect pages comply with privacy and marketplace review policies.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill explicitly recommends multi-channel customer outreach including SMS, WhatsApp, email, and inserts, but it does not require consent checks, privacy notices, suppression handling, or platform-specific messaging compliance. In an ecommerce context, this can lead operators to contact customers through regulated or policy-restricted channels without lawful basis or opt-in, creating privacy, anti-spam, and marketplace-enforcement risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The worked example introduces an off-platform QR-code landing page and routes dissatisfied buyers to support email first, but omits warnings about data collection, tracking, consent, and marketplace policy limits for off-platform review flows. This is risky because such flows can capture customer identifiers or influence review pathways in ways that create privacy exposure and can be interpreted as review manipulation or non-compliant routing if not tightly controlled.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The 'Negative-feedback path' section asks for separate insert and email wording plus a support route for dissatisfied customers, which can enable review gating by diverting unhappy buyers to private support before they leave public reviews. In a skill explicitly designed to increase review rates and star averages across ecommerce platforms, this context makes the pattern more dangerous because it can be used to suppress negative reviews while still presenting a compliance checkbox that claims no gated reviews.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file is in scope for vague-trigger checks. The trigger value 'Pack' does not clearly specify the activation condition, scope, or exclusions, making it ambiguous when the associated action should occur.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.