Security audit

数学错误DNA

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese K12 math error-analysis skill with persistent learner-profile behavior, but its data use, consent checks, sharing limits, and crisis handling are disclosed and aligned with its educational purpose.

Install this only for the intended Chinese K12 tutoring context or after localizing language, curriculum, consent rules, and crisis-contact guidance. Because it works with student learning records and anxiety signals, verify that profile storage, parent sharing, cross-skill sharing, and reminders are disabled by default unless the user or guardian has consented.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is authored entirely in Chinese and defines user-facing flows, triggers, and outputs only in Chinese, without any mechanism to detect or honor the user's preferred language. This can cause users to misunderstand consent, privacy controls, crisis handling, or data-sharing choices, which is especially risky in a skill that processes student records and anxiety-related signals.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger examples include broad, everyday phrases such as '我数学太差了' that can be said in many contexts, including emotional venting rather than an intentional request to invoke this skill. That increases the risk of unintended activation, unnecessary processing of sensitive educational/anxiety-related data, and accidental cross-skill handoffs in a system that stores learner profiles.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The document is entirely written in Chinese and is explicitly scoped to a Chinese middle-school context, but it does not state that language use is optional or provide any language-choice guidance. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 该文件标题与全文说明均仅以中文呈现，未见任何关于可选择其他语言或面向特定中文场景的说明。根据规则，若技能内容强制单一语言而没有用户选择或明确的合理限定，属于自然语言层面的政策风险。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The entire skill file is written in Chinese and defines defaults for Chinese school grade bands, curricula, and policies without any indication that the skill offers a language choice or that it is explicitly limited to a China-specific audience. Under the policy, locale-specific constraints should either be optional for the user or clearly documented as justified regional scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The text states the repository is designed for Mainland China Chinese K12 scenarios, with simplified Chinese wording and Mainland China safety/help channels as defaults. Although it includes adaptation steps for other regions, it still sets a fixed language/locale default rather than offering user choice or explicit opt-in, which matches the policy category for locale constraints.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.