Back to skill

Security audit

爆款标题生成器技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language social media title generator with no code execution, credential access, persistence, or external data flow.

Install this if you want Chinese social media title suggestions. Be aware that it may activate on general title-writing requests and tends to force a Chinese formatted output, so invoke it explicitly or adjust instructions if you need another language or a less prescriptive format.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description and behavior are effectively fixed to Chinese, with no user language negotiation or documented scope limitation. This can lead to incorrect-language responses, reduced usability, and accidental mishandling of requests in other languages, especially because some English triggers are included but the output requirements remain Chinese-centric.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad enough to activate on many ordinary requests such as '生成标题' or '写标题', which can cause the skill to intercept unrelated conversations and override user intent. While this is not code execution or data exfiltration, it creates routing ambiguity and can degrade safety and reliability by invoking a prescriptive output format in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire reference document is written exclusively in Chinese and prescribes Chinese platform-specific title formulas, tone, and wording without indicating that language selection is optional. This can violate a language/locale policy when a skill is expected to support user choice rather than forcing a specific language by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.