ClawHub
Back to skill

Security audit

Programmatic Seo

Security checks for vulnerabilities and agentic risk

Overview

This is a plain guidance skill for planning programmatic SEO pages, with no executable code, persistence, credential handling, or hidden high-impact behavior.

Install this if you want help planning programmatic SEO campaigns. Be aware it may activate on adjacent bulk page-generation requests, so users should confirm the task is truly SEO-driven and at scale rather than a one-off page, general SEO audit, or content strategy request.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description includes broad activation guidance such as "Use this whenever someone wants to create many similar pages targeting different keywords or locations." That phrasing is wider than the explicit pSEO trigger list and could overlap with ordinary website/content requests that are not truly programmatic SEO tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The eval explicitly rewards triggering on casual phrasing for programmatic SEO requests without specifying tighter routing boundaries, which can train or validate overly broad skill activation. In practice, this increases the chance the skill is invoked for ambiguous SEO requests that should be handled by other skills, leading to incorrect guidance, misrouting, and reduced safety controls around task scoping.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.