ClawHub
Back to skill

Security audit

amazon-listing-optimizer

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill provides local listing checks without account access or hidden actions, but its automated checks are limited.

Manually review rewritten copy, category limits and claims: a clean report is not proof of Amazon compliance. Choose an output folder where replacing lint-report.md is acceptable. The optional unsigned Windows app requires a separate trust decision; this verdict does not establish its safety ([publisher repository](https://github.com/rapidworker1/Multiple-AI-models-Toolkit)).

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code is a basic listing linter, not a listing rewriter. Its phrase checks align with part of the description, but it neither interprets product specifications nor produces revised listing copy. Section checks only search for label substrings, and length checks apply to every raw line. Local input reading and report writing are ordinary supporting operations; no unrelated access or external actions are evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.