ClawHub
Back to skill

Security audit

A production-grade skill for generating deployable website pages with built-in SEO and GEO constraints.

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown SEO page-writing skill with no code execution, persistence, credential handling, or hidden data access.

Install only if you want a structured SEO/GEO website-page drafting workflow, especially for Chinese-first output. Review generated claims before publishing and use current web research for competitors, search policies, pricing, ratings, or other time-sensitive facts.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (13)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger criteria are extremely broad, including cases where users merely want to turn 'product positioning, a topic, or page intent' into a page and instructing the skill to trigger even when SEO is not explicitly requested. This can cause inappropriate routing of ordinary writing tasks into a rigid SEO workflow, overriding user intent and increasing the chance of irrelevant or policy-conflicting outputs.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
## Non-negotiable SEO and GEO rules

Always obey:
- one page = one core intent
- no keyword stuffing
- no hidden text or deceptive SEO

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Forcing Chinese output by default without user opt-in can cause the skill to ignore the user's language, reduce usability, and produce unexpected or inaccessible responses. In a multi-lingual assistant environment, this is a control-flow problem because the skill may override higher-level conversational expectations and degrade task correctness.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese throughout its instructions and templates, effectively imposing a specific language on users of the skill. The policy for SQP-3 flags language or locale constraints when the skill does not provide user opt-in or explain that the restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The required sections are specified entirely in Chinese, and the eval prompts/expectations throughout the file also assume Chinese-language output. This creates a natural-language policy risk because the skill appears to force a specific language/locale without offering user opt-in or documenting that the skill is intentionally Chinese-only.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The eval set treats an underspecified prompt ("给我做一个页面，主题是 AI Agent。") as a normal success case without tightly constraining page type, audience, or safety boundaries. In a skill that is configured to trigger broadly for many page-generation tasks, this can cause inconsistent behavior, overconfident fabrication of assumptions, or generation of mismatched content that may be deployed without proper review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire guidance document is written as mandatory Chinese-language operating instructions for the skill, with no indication that users may opt into another language or locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document content is written as a mandatory operating contract in Chinese and does not indicate that language choice is optional or configurable. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file hard-requires Chinese output for all page-generation tasks without giving the user a language choice or documenting a necessary locale restriction. In a general-purpose page-generation skill, this can silently override user intent, produce incorrect-language deliverables, and create downstream publishing, compliance, and accessibility issues if pages are deployed to the wrong audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Line L009 states the file content in Chinese and the document consistently instructs behavior in that language, but there is no indication that users may choose another language or that the skill is region-specific. This can violate language/locale policy when a skill implicitly forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Lines L009-L010 state the file defines quality gates for the skill in Chinese and present the requirements entirely in Chinese, which effectively imposes a specific language/locale. The file does not provide user opt-in, alternatives, or a documented region-specific justification for this language constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document is written entirely in Chinese and provides no indication that language choice is optional or that the skill is intentionally limited to a Chinese-speaking or region-specific context. The policy explicitly flags language or locale constraints when a specific language is forced without user opt-in or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The line states that the skill 'must' follow these rules, and the document is written as a binding instruction in Chinese without offering any user language choice. Per the policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless clearly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.