Security audit

医械注册申报资料编写

Security checks for vulnerabilities and agentic risk

Overview

This is a document-writing aid for medical-device registration dossiers, with no executable code, persistence, credential use, or hidden high-impact behavior found.

Use this as a drafting and checklist assistant only. Verify regulatory details against current official agency sources and qualified RA/legal review, especially for live submissions, and avoid providing customer names, prices, unpublished project details, or other sensitive business data.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (5)

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The document is written entirely in Chinese and includes a prescriptive instruction that branding attribution must use a specific Chinese-language form. This is a natural-language locale constraint without any opt-in, alternative language option, or stated region-specific justification.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger list includes broad natural-language phrases such as “帮我写/整理注册申报资料” and “注册资料怎么排,” which can match common user requests and cause the skill to activate unintentionally. In a regulated medical-device context, accidental invocation is risky because users may receive dossier-generation guidance without explicitly choosing this specialized workflow, increasing the chance of misplaced reliance or context confusion.

Natural-Language Policy Violations

Low

Confidence: 85% confidence
Finding: The skill's display name, headings, workflow, and warnings are presented in Chinese, while the file does not state that the skill is China-specific or require user opt-in for Chinese output. Because the skill covers multiple jurisdictions including FDA, MDR, and PMDA, forcing one language without an explicit choice may violate language/locale policy expectations.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The package name and author fields are written entirely in Chinese with no indication that users can choose another language or that the skill is intentionally restricted to a Chinese-language audience. Under the policy for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: The keys in the scores object are presented entirely in Chinese, but the file does not state that this skill is region-specific or that users opted into Chinese output. This can violate a language/locale policy when artifacts are forced into a specific language without documented justification.

Static analysis

No suspicious patterns detected.