Security audit

medical-device-code-review

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only medical-device code review guide with no executable behavior, persistence, credential handling, or hidden authority, though its trigger wording is broader than its intended domain.

Install this skill if you want Chinese-focused medical-device software review guidance. Be aware that its broad trigger phrases may make it appear during ordinary code review requests, and its regulatory guidance should be validated by qualified medical-device compliance professionals before use in submissions or safety decisions.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger description includes very broad, everyday phrases such as '帮我看看代码', '有bug吗', and '代码有问题吗', which can cause the skill to activate on many generic coding requests outside the intended medical-device context. Because this skill is specialized for safety-critical medical software and frames its review around regulatory/medical assumptions, unintended activation could misroute ordinary code-review requests and produce inapplicable compliance or safety guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill description is written to operate in Chinese and emphasizes Chinese regulatory documentation without indicating any user language choice. This can lead to mismatches where users expecting another language receive compliance or safety guidance they cannot accurately understand, increasing the chance of misinterpretation in a safety-sensitive domain.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The entire skill content is presented only in Chinese and does not indicate that the user can choose another language. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue unless the regional constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.