Back to skill

Security audit

SEO Optimizer 违禁词检查

Security checks for vulnerabilities and agentic risk

Overview

This is a simple SEO and Chinese advertising-law checklist skill with no executable code, persistence, credential use, or hidden data access.

Install only if you want SEO help for Chinese social media or Chinese advertising-law wording checks. For general SEO, ask the agent to confirm the target platform, language, and region before applying this skill's recommendations.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is explicitly scoped to Chinese social media and Chinese advertising-law compliance without indicating any user choice or opt-in, which can cause the agent to apply locale-specific rules inappropriately. This is mainly a context-mismatch risk that may produce irrelevant guidance or compliance checks for users targeting other regions or platforms.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation criteria are broad enough to match common, generic requests such as SEO, keyword optimization, and compliance check, which can cause the skill to activate outside its intended narrow context. In an agent system, over-broad routing can lead to inappropriate behavior, incorrect assumptions about user locale/platform, and unintended processing of unrelated content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.