Back to skill

Security audit

SEO Competitor Gap Analysis - SEOmatic

Security checks for vulnerabilities and agentic risk

Overview

This SEO skill is purpose-aligned and disclosed, though users should understand it can stage SEO work and use approval-capable SEOmatic task tools.

Install only if you are comfortable connecting SEOmatic to your Search Console/site data and letting it stage SEO task cards. Review each staged task, cost label, and approval request carefully; do not approve a task unless you want SEOmatic to execute that specific site change.

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 (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s stated purpose is competitor-gap analysis, but the instructions extend into operational task staging and possible approval flows. This creates scope creep from analysis into action, increasing the chance an agent with available credentials could prepare or influence site-changing tasks that the user did not explicitly request in the context of a competitive analysis.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Including approval-capable workflow guidance in a competitor-gap skill is risky because it normalizes transition from insight generation to execution authority. Even though the text says not to approve on the user’s behalf, exposing task_manage approval-related capability in this context broadens the attack surface and could enable unsafe actions if an agent misinterprets user intent or is prompt-injected elsewhere.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.