LINE Rich Messages

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 9:30 PM UTC
• Version: 1.0.5

Overview

This skill is a LINE rich-message template guide with no executable code or bundled credentials, though users should note its LINE plugin setup and Chinese-language template text.

Before installing, confirm you intend to use this with the OpenClaw LINE plugin and are comfortable enabling inline button capabilities. Review and localize the Chinese sample text if your users are not Traditional Chinese readers. The README's file-delivery references appear stale; rely on SKILL.md, which explicitly excludes file upload or sharing workflows.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Memory Poisoning: Persistent Context Injection, Context Window Stuffing, Memory Manipulation
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Memory Manipulation

High

• Category: Memory Poisoning

Content

- **No file delivery**: For security, this skill intentionally does **not** include any workflow for uploading/sharing files (e.g., Google Drive). If you need file delivery, implement it in a separate, tightly-scoped skill with explicit allowlists and safeguards.
- **Guided Choices**: If you ask a question with 2-4 fixed answers, always include `[[quick_replies: ...]]`.
- **Structured Data**: Use Markdown tables for any multi-point information (e.g., flight times, order items).
- **Destructive Actions**: Use `[[confirm: ...]]` for actions like "Delete Memory" or "Cancel Project".
- **UX Limitation (Crucial)**: Text within Flex Messages (including Markdown tables and auto-converted replies) **cannot be selected or copied** by the user. 
  - **Rule**: If the data is meant to be copied (e.g., SSH keys, IDs, URLs), **always send it as plain text** without Markdown formatting or directives that trigger Flex conversion.

• Confidence: 80% confidence
• Finding: Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The skill includes normative instructional text in Chinese, such as 'Rich-UI 優先', and later substantial guidance entirely in Chinese. Because the file does not state that the skill is intended only for Chinese-speaking users or offer an opt-in language choice, it creates a language/locale policy concern.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: Lines 47-52 contain key usage instructions entirely in Chinese, including the recommended 'golden path' and constraints around sending JSON and avoiding direct API calls. Presenting essential instructions in a fixed language without documenting a locale-specific justification can violate language/locale policy expectations.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: This markdown file contains multiple user-facing template strings in Traditional Chinese, such as button labels, prompts, and descriptions, but does not indicate that the skill is region-specific or that users can opt into another language. That creates a natural-language locale policy concern because the file effectively prescribes a single language for generated content.

Static analysis

No suspicious patterns detected.