Back to skill

Security audit

SEO article cluster builder

Security checks for vulnerabilities and agentic risk

Overview

This SEO content skill is coherent and disclosed, with the main caveat that several templates are Vietnamese-specific and may need adjustment for other sites.

Install this if you want a structured SEO cluster-writing workflow and are comfortable with the agent researching your site and competitors online. Before using it for non-Vietnamese sites, explicitly tell the agent the target language, locale, currency, and UI labels to use so the vi/vi-VN templates are not copied unchanged.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (7)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · references/phase4-output.md (reported line 25)May include surrounding context.

md
<body>
<div class="page">

  <!-- 1. PAGE HEADER (.pg-hd) -->
  <!-- 2. AUDIT BOX (.audit) — pre-existing issues found in research -->
  <!-- 3. TABLE OF CONTENTS (.toc) — links to each article section -->
  <!-- 4. ARTICLE BLOCKS (.art) × N — one per article -->

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger block is very broad and explicitly says to 'always use this skill' for common SEO/content-cluster requests. That can cause unintended invocation on loosely related user prompts, leading the agent to fetch sites, perform external research, and follow a rigid workflow the user did not request. In an agent setting, overbroad activation is a real security/control issue because it can override user intent and expand tool use unnecessarily.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill states that it encodes the exact workflow used for Vietnamese-language clusters for pinata.vn, and the listed trigger phrases also mix in Vietnamese examples, but the document does not state that language or locale should be chosen based on user preference. This can bias outputs toward a specific locale without explicit opt-in or a documented region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This CSS file includes instructional comments entirely in Vietnamese, such as usage guidance about where to copy or link the stylesheet. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation, and no alternative language choice or locale justification is provided in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown explicitly instructs the operator to search for the target keyword in Vietnamese, which imposes a specific language/locale on skill behavior. The file does not offer a user choice, opt-in mechanism, or explain that the skill is limited to a Vietnam-specific compliance or regional use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The schema template hard-codes "inLanguage": "vi-VN" for all articles, which can cause incorrect metadata when the client site or requested output language is not Vietnamese. This can lead to mislabeling of content for search engines and downstream systems, creating integrity and compliance issues if users expect language to follow site settings or explicit instructions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The template hard-codes lang="vi", Vietnamese UI text, and locale-specific output without checking user preference or target audience. In an agent skill, this can cause silent misdelivery of content in the wrong language/locale, leading to incorrect publication output, SEO mismatches, and user deception if the agent presents content as generally applicable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.