Excel / WPS Table Diagnosis

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 3:59 AM UTC
• Version: 1.0.0

Overview

This skill is a focused spreadsheet-assistance guide that gives Excel/WPS formula and cleanup advice without hidden execution, credentials, persistence, or network behavior.

This skill is reasonable to install for spreadsheet help. Because its suggestions can affect workbook data if acted on, use a copy for important files, confirm lookup keys and duplicates before merging sheets, and keep direct spreadsheet changes user-approved.

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

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Hidden Instructions

High

• Category: Prompt Injection

Content

# Quick Start

## Project Goal

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High

• Category: Prompt Injection

Content

# Quick Start

## Project Goal

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The manifest describes invocation as 'Use $excel-wps-table-diagnosis to inspect this table and suggest a practical Excel/WPS-friendly way to clean, match, summarize, or troubleshoot it,' which covers a wide range of common spreadsheet tasks without clarifying when the skill should or should not activate. There are no exclusion conditions or negative examples to constrain scope, increasing the chance of unintended invocation in ordinary spreadsheet-help contexts.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: This markdown file repeatedly describes invocation with generic phrases like 'Use the project' across multiple common spreadsheet tasks. Because it does not define explicit trigger phrases, boundaries, or negative examples, the activation guidance is broad enough to overlap with many ordinary requests and could cause unintended skill invocation.

Natural-Language Policy Violations

Low

• Confidence: 80% confidence
• Finding: The README includes Chinese-language instructions and examples as part of the core skill description, but it does not state that multilingual output is optional or user-selected. Under the language/locale policy rule, imposing a specific language without opt-in can be a policy concern, even if the document is otherwise bilingual.

Missing User Warnings

Low

• Confidence: 79% confidence
• Finding: This markdown file instructs matching two sheets by `Customer ID` and recommends lookup formulas, but it does not warn that incorrect keys, formatting mismatches, or unresolved duplicates can lead to inaccurate merges affecting user data. Because SQP-2 applies to markdown files, omission of a caution about data-impacting behavior is a quality/safety gap.

Static analysis

No suspicious patterns detected.