Security audit

物理错误DNA

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese K12 physics learning-profile skill that stores and shares only scoped learning-error data when the relevant user consents are enabled.

Before installing, confirm this will be used in the intended Mainland China Chinese K12 context, and review the consent settings for student profiles, cross-skill sharing, reminders, parent-visible summaries, and deletion/export rights. Outside that context, localize curriculum assumptions and crisis-contact guidance first.

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 (12)

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: 93% confidence
Finding: The title and the full document are written in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally restricted to a Chinese-language or China-specific context. Under the policy, forcing a specific language without user opt-in is a reportable locale-policy issue.
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: 94% confidence
Finding: This JSON schema includes hard-coded Chinese-only enum values such as consent subjects, along with Chinese-only descriptions and examples throughout the file. Because the skill does not indicate that it is intentionally limited to a Chinese locale or provide any user opt-in or alternative locale handling, this creates a natural-language locale policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file is entirely written in Chinese and provides operational skill guidance without indicating that users may choose another language or that the skill is limited to a Chinese-speaking or China-specific deployment. The policy requires flagging language or locale constraints when they are imposed without user opt-in or clear justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This schema embeds natural-language instructions and enumerated value labels in Chinese, such as the note on skill scope and later user-facing status/dimension labels, but does not indicate that the protocol is intentionally China/Chinese-only or provide any language/locale opt-in. That can violate the policy against forcing a specific language without user choice or explicit justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The schema requires Chinese-only enum values for basicDimension, and similar Chinese-only status values appear elsewhere. Because these values may propagate across skills and user-facing outputs, the file effectively enforces a specific language without documenting a justified regional constraint or offering alternatives.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The status enum uses Chinese-only values, which can impose a fixed locale on downstream systems and outputs. The file does not state that this is a region-specific compliance requirement or otherwise justify the language constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The document states that the repository is designed for ‘中国大陆的中文 K12 场景’, with simplified Chinese wording and mainland-China crisis channels as defaults. This is a natural-language locale constraint, and while it notes operators must localize before deployment elsewhere, it does not offer end users a language/locale choice or opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The markdown lists invocation phrases such as “查看我的[档案/记录]”, “更正我的[档案]”, and “删除我的[档案]” as control entrances, but it does not define where these phrases apply, how exact they must be, or examples of similar phrases that should not trigger the skill behavior. Because these are natural-language triggers in documentation, the lack of specificity could lead to unintended invocation in ordinary conversation about records or deletion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The title and introductory description are entirely in Chinese, and the file does not indicate that language selection is optional or that the resource is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The file presents all instructional content exclusively in Chinese and does not mention any language choice, opt-in, or region-specific justification. Under the policy rule for natural-language constraints, this can be treated as a locale/language restriction that is not documented as optional.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.