Security audit

ym-brand-voice-check

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only brand voice proofreading skill with no hidden code, network use, persistence, or automatic modification behavior.

Installers should expect a Chinese-language brand voice checker. Review the broad trigger terms if accidental activation matters in your environment, and do not treat its risk-word hints as legal compliance advice.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The manifest trigger list contains short, generic phrases such as '品牌语气', '语气校对', and 'brand voice' without contextual constraints. In an agent routing system, these broad triggers can over-match benign user text, causing accidental skill activation and misrouting of tasks or disclosure of user content into an unnecessary transformation workflow.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The usage examples include broad natural-language phrases like '这段是不是不太像我们', which can match ordinary conversation outside a clear proofreading request. This can cause unintended invocation of the skill and lead the agent to enter a constrained rewriting/auditing mode when the user may have meant a general discussion instead.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This markdown file presents all instructions and policy guidance exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the content is intentionally limited to a Chinese-speaking context. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The template headings, instructions, and placeholders are all in Chinese, which constitutes a language-specific constraint in the skill content. Under the policy, forcing a specific language without user opt-in or an explicit justified regional scope is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 76% confidence
Finding: The statement “不校对非中文语种的细微语感” sets a language capability constraint that favors Chinese without offering a user choice or an explicit locale-specific justification. This can be read as a language policy limitation rather than a documented opt-in preference.

Static analysis

No suspicious patterns detected.