Cn Percent Calculator

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 7:30 AM UTC
• Version: 1.2.6

Overview

This is a local Chinese-language percentage calculator with no network, credential, persistence, or privilege behavior in its runtime code.

Installers should expect a simple local calculator with Chinese prompts and output. The promotional links in the README are unrelated to calculation, so avoid following them unless you trust the publisher.

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

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: This markdown file describes activation through phrases prefixed with "千策" but does not specify whether that is the only valid trigger, what contexts it applies in, or any negative examples. The lack of trigger scope makes invocation conditions ambiguous and could cause unintended activation if the phrase overlaps with ordinary assistant usage.

Natural-Language Policy Violations

Low

• Confidence: 81% confidence
• Finding: The skill name, description, usage, and examples all prescribe Chinese-language interaction, but the file does not indicate that this is optional or limited to a China-specific deployment. That can be a language-policy concern when users are not given a choice of locale or language.

Description-Behavior Mismatch

Low

• Confidence: 84% confidence
• Finding: The skill is presented throughout as a pure local calculator with no API usage, focused on percentage-related computations. The addition of vendor marketing links and a call-to-action to visit an external site introduces behavior/purpose content outside that described calculator scope, creating a mild description-to-content mismatch.

Natural-Language Policy Violations

Low

• Confidence: 92% confidence
• Finding: This code file presents its title and user-facing description entirely in Chinese, and later user-facing prompts and labels are also Chinese-only. Under the policy rule for natural-language violations, forcing a specific language without opt-in or documented regional justification can be a locale-policy issue.

Natural-Language Policy Violations

Low

• Confidence: 96% confidence
• Finding: The argparse description, help text, error message, and printed result labels are all hardcoded in Chinese, giving users no language choice. This is a natural-language policy concern because the skill enforces a specific language across its interface without explicit opt-in or documented scope limitation.

Static analysis

No suspicious patterns detected.