Security audit

ACG-Rust 教学工具

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language Rust teaching skill with a local Python demo script and no evidence of hidden access, exfiltration, persistence, or unsafe authority.

Install this if you are comfortable with Chinese-language Rust learning material and anime-based analogies. The progress feature appears local and temporary in the current code, but users who need privacy guarantees should ask the publisher to document that behavior explicitly.

A.I.G

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

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This Python file is in scope for natural-language policy checks. The title, docstrings, method names, user-facing strings, and examples are entirely Chinese, and the skill does not indicate that users can select another language or that the skill is intentionally limited to a Chinese-speaking context.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: The skill explicitly advertises progress tracking, but the documentation does not disclose what learner data is collected, whether it is persisted, or where it is stored. While this is not code execution or privilege abuse, it creates a privacy and transparency risk because users may unknowingly provide or generate personal study-history data that is retained locally or elsewhere.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the skill is intentionally region-specific. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This markdown file presents all instructional and descriptive content in Chinese only, with no indication that users may choose another language or that the restriction is required for a specific locale.

Static analysis

No suspicious patterns detected.