ClawHub
Back to skill

Security audit

SEO Delivery Guard

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only SEO governance skill with clear limits around credentials, deployment, account changes, and external writes.

Install only if you want an agent to apply SEO-focused delivery and release checks. Keep its use scoped to specific SEO work, and continue to require explicit approval before deployments, search-console changes, URL submissions, or use of sensitive project data.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation while describing its scope in broad terms, which can cause the agent to activate this governance skill for loosely related development or release tasks without an explicit user request. In a release-governance context, unintended activation can steer workflows, impose search-facing constraints, or influence code-review and deployment decisions based on ambiguous SEO relevance, creating prompt-routing and authority-confusion risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This file is entirely presented in German, which can be read as a locale-specific constraint when taken on its own. Under the policy, language forcing is a violation unless the skill explicitly offers a language/locale choice or clearly documents the constraint as justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Este archivo de documentación está íntegramente en español y no incluye una nota dentro del propio archivo que ofrezca elección de idioma o explique una limitación regional. Según la política de lenguaje/locale, forzar un idioma sin opt-in explícito puede constituir una infracción de política en lenguaje natural.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This README variant is written in Korean and the language navigation highlights multiple available translations, but there is no indication in the content that Korean is mandatory or that users may choose another language version. Because the skill documentation presents language-specific content, this can be read as a locale-specific constraint unless the user is clearly offered a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

Este README está em português do Brasil, o que isoladamente poderia parecer uma restrição de idioma. Porém a própria linha lista várias alternativas de documentação em outros idiomas, oferecendo escolha explícita ao usuário; portanto isso não constitui violação real de política de idioma.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file presents the skill documentation in Vietnamese and labels this variant as 'Tiếng Việt' without any statement that the user chose this locale or that the skill is region-specific. Under the language/locale policy, forcing a specific language is a violation unless the locale choice is explicit or clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.