ClawHub
Back to skill

Security audit

LaunchFast PPC Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon PPC helper that researches keywords and generates a user-reviewed bulk upload file, with no hidden execution or direct account changes.

Install only if you intend to use LaunchFast for Amazon PPC research. Before uploading any generated file, review campaign name, bids, daily budget, keywords, and ASIN targeting in Amazon Seller Central.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest lists invocation examples such as "find keywords for my Amazon listing" and "build a PPC campaign for [product]" without clear exclusion conditions or tighter scope boundaries. These phrases are broad enough to match general marketing or listing-help requests, which could cause unintended activation of this specific bulk-upload PPC workflow.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill goes beyond keyword research and instructs the agent to write a bulk-upload file directly into the local Downloads directory. That introduces an unnecessary local file-write side effect that is not justified by the stated MCP requirement, and if followed automatically it could create or overwrite files on the host without clear user approval. In this context, the file contents are also operationally sensitive because they can later be uploaded to Amazon Ads and trigger campaign changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.