Security audit

检查报告解读

Security checks for vulnerabilities and agentic risk

Overview

This is a small medical-report reference skill with no code execution, persistence, credential handling, or hidden data access, though its broad triggers and Chinese-focused content should be understood before use.

Install only if you want Chinese-focused assistance interpreting imaging, ECG, or related report wording. Treat it as educational context and confirm urgent or abnormal findings with qualified medical professionals; broad triggers may activate it when terms like CT, MRI, or ECG appear.

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)

Natural-Language Policy Violations

Medium

Confidence: 82% confidence
Finding: Most of the operational content and trigger phrases are Chinese-only, which effectively forces a specific language/locale for use. The file does not state that the skill is region-specific or offer users a language option, so this constitutes a natural-language policy concern.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list includes very generic terms such as "CT", "MRI", "ECG", and "胸片", which are likely to appear in ordinary conversation and unrelated medical text. This can cause unintended invocation of the skill, leading the agent to provide quasi-clinical interpretation in contexts where the user did not explicitly request it, increasing safety and scope-control risk in a medical setting.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The skill name is presented in Chinese while the description is in English, which implies a locale/language assumption without any stated user opt-in or language-selection behavior. This can create a natural-language policy issue if users are forced into a language context that is not explicitly chosen or documented.

Static analysis

No suspicious patterns detected.