Back to skill

Security audit

Affiliate Marketer Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only affiliate marketing coaching skill with no executable behavior, but users should notice one inconsistent recommendation around paid link placements.

Before installing, treat this as a coaching/reference skill rather than an automation tool. Be careful with the paid niche edits advice, because buying editorial links can violate search-engine or affiliate-program rules; favor disclosed sponsorships, editorial outreach, digital PR, and compliant link acquisition instead.

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
  • 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 (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly says it should refuse link-buying schemes, but later recommends paid niche edits as a tactic. That inconsistency can cause the agent to provide guidance on paid link acquisition that may violate search-engine policies and affiliate program terms, exposing users to penalties, delisting, or account termination.

Content

No source excerpt is available for this finding.

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 49)May include surrounding context.

md
## Phase 1 — Niche & site selection (do this *before* writing one article)

The single biggest cause of failed affiliate sites: niche picked for traffic potential without checking commission economics. 100K visits/mo with $0.50 RPM = $50; 100K visits/mo with $30 RPM = $3,000.

### Niche-fit gate (must pass all 4)
1. **Buyer intent density** — at least 30% of niche keywords are commercial-intent (review / comparison / "best", "vs", "alternative", "review", "X for Y"). Pure informational niches starve.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This section directly labels paid niche edits as a workable backlink tactic despite the earlier refusal policy on link-buying schemes. In context, this is more dangerous because the skill is an operational playbook, so users may act on the contradictory advice and engage in deceptive SEO practices that create legal, contractual, and platform-enforcement risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.