ClawHub
Back to skill

Security audit

article-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown SEO/article-page guidance skill whose web research behavior is disclosed and aligned with its purpose, though users should avoid sending confidential drafts into searches.

Install is reasonable for SEO article-page work. Before using it on unpublished, internal, or sensitive articles, ask the agent to skip search or to use only generic/redacted queries so private draft text and product details are not sent to external search providers.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger description is very broad and includes common phrases like 'optimize article for SEO' and 'analyze ranking articles,' which can cause the skill to activate for generic requests that may not need this specific workflow. Misactivation is risky here because the skill then pushes mandatory research/search behavior and prescriptive output structure, potentially causing unnecessary external lookups or use of the wrong specialized skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to proactively search when inputs are missing, but it provides no requirement to notify the user that external web access may occur or that user/article data may be used to form queries. This can leak sensitive project, product, or draft content to external services without informed consent, especially during analysis of unpublished articles or internal company material.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This section makes external search the default for article analysis and requires outputting search results unless the user explicitly opts out. Default-on external enrichment increases the chance of unintentional disclosure of sensitive context and creates a data-handling risk because users may not realize their request will trigger third-party searches.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.