Back to skill

Security audit

middle-aged-social-comment

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-assistant skill for WeChat-style social commentary, with no executable code, persistence, credential access, or hidden behavior found.

Install this if you want a Chinese WeChat-public-account style writing helper for middle-aged social commentary. Be aware that it may search recent online trends and may activate for broad commentary-writing prompts unless your agent lets you control skill routing.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The changelog describes the skill's core workflow and writing-style rules entirely in Chinese, which indicates a language-specific behavior. There is no accompanying note that this language choice is optional or limited to a justified region-specific context, so it may conflict with language/locale choice expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description includes trigger phrases like '按公众号风格写' and '写一篇评论文章', which are broad enough to match many generic writing requests outside the intended niche of middle-aged social commentary. This can cause unintended skill activation and steer unrelated user tasks into a highly specific ideological/style workflow, reducing user control and potentially causing prompt-routing errors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is written to operate in Chinese for a specific cultural and platform context without any opt-in or language negotiation. If auto-invoked for users who did not request Chinese or this locale, it may override user preferences and produce unusable or inappropriate output, especially in multilingual environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The skill description is entirely in Chinese and explicitly targets "30-50 岁中年读者的微信公众号" content, which suggests a fixed language/locale and audience framing without stating that users may choose another language or locale. Under the policy rule, fixed language behavior should be documented as optional or clearly justified as region-specific.

Content

No source excerpt is available for this finding.