Back to skill

Security audit

Affiliate Marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only affiliate marketing guidance skill with optional, disclosed local continuity notes and no automatic account, payment, network, or file actions.

Before installing, decide whether you want the optional continuity behavior. If partner names, payout details, fraud concerns, or compliance notes are sensitive, use the skill statelessly or keep the local ~/affiliate-marketing/ notes minimal. Separately approve any real outreach, account changes, network access, or payout changes if another tool workflow is used.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (3)

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 · economics.md (reported line 26)May include surrounding context.

md
## Ceiling Rule

Never recommend commission increases without checking:
- gross margin
- assisted vs incremental conversion
- refund or clawback rate

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · playbooks.md (reported line 24)May include surrounding context.

md
- pause suspicious payouts
- review sources, coupon spread, and lead quality
- classify abuse vs tracking error vs normal variance
- document permanent rule changes before reactivation

## 4. Margin Rescue Sprint

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The setup text instructs activation for a wide range of loosely bounded business topics, including general partner recruitment, attribution cleanup, and ongoing help. This broad trigger surface can cause the skill to activate for common business-assistance requests outside its intended scope, leading to unnecessary memory writes or overly influential skill steering in unrelated conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.