ClawHub
Back to skill

Security audit

Amazon PPC

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Amazon PPC planning guide with no code, credential access, API connection, persistence, or hidden agent-control behavior.

Before installing, understand that this skill can influence advertising spend decisions. Use it as planning support, verify margins and campaign data yourself, and apply any bid or budget changes manually in Amazon Ads.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · assets/ppc-quality-checklist.md (reported line 21)May include surrounding context.

md
- [ ] All four tiers planned (Research, Performance, Brand Defense, Competitor)
- [ ] Campaign naming convention documented and applied consistently
- [ ] No duplicate campaigns targeting the same match type + keyword combination
- [ ] Each campaign has a clear stated purpose
- [ ] Daily budgets set with minimum 10× Max CPC floor

### Keywords

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
1. **Launching with only auto campaigns** — Auto gives Amazon maximum control and often routes budget to irrelevant terms. Always pair with at least one manual exact campaign.

2. **Setting ACoS targets without checking margin** — A 30% ACoS target on a product with 25% margin is a guaranteed loss. Always derive target ACoS from unit economics first.

3. **Never adding negative keywords** — Even excellent products will have irrelevant search volume. Not adding negatives is an ongoing tax on every campaign dollar.

Static analysis

No suspicious patterns detected.