Security audit

AI急救指南

Security checks for vulnerabilities and agentic risk

Overview

This first-aid skill is not agentically malicious, but it needs review because some emergency medical guidance is unsafe or under-scoped.

Install only after reviewing and correcting the medical content against current certified first-aid sources, especially choking/unresponsive-victim instructions. Treat it as China/Chinese-language oriented unless the publisher adds clear locale selection and local emergency-number handling.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (12)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This guidance for an unconscious choking victim is medically unsafe because it directs rescuers to continue abdominal thrusts and perform finger-sweeps, instead of transitioning promptly to CPR and removing an object only if it is clearly visible. In a first-aid skill, incorrect emergency instructions can directly cause delayed oxygenation, airway trauma, or worsening obstruction during a life-threatening event.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The embedded HTML template hard-codes lang="zh-CN", which directs generated output toward a specific locale. The file does not state that the skill is region-specific or that users can opt into another language/locale, so this is 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: 91% confidence
Finding: This file presents all user-facing safety guidance in a single forced language, which can violate language/locale policy when no opt-in or alternative is provided. Users who do not read Chinese may be unable to understand critical emergency instructions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The entire skill is written only in Chinese and does not indicate that language can be selected by the user. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, and nowhere indicates that the language is optional or limited to a Chinese-speaking context. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale policy issue.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The table states that adult back blows are simply incorrect and adds contradictory reasoning, which is overbroad and can mislead readers about accepted choking-response options in some first-aid protocols. In an emergency reference, oversimplified or inaccurate prohibitions may cause hesitation or prevent use of appropriate airway-clearance steps.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This section recommends advanced interventions and restricted items such as tourniquets, hemostatic agents, cervical collars, AEDs, nitroglycerin, aspirin, epinephrine auto-injectors, insulin, and inhalers, but does not place an immediate, prominent warning beside those entries to require training, clinician guidance, or emergency services involvement before use. In a first-aid skill, users may treat the checklist as actionable advice during a crisis, increasing the risk of misuse, delayed professional care, medication errors, or harm from inappropriate application.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains user-facing medical guidance exclusively in Chinese, and nowhere indicates that the skill is China-specific or that the user can opt into this language. Under the language/locale policy, forcing a specific language without user choice or a documented justification is 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: 91% confidence
Finding: The file presents all instructions in Chinese and does not state that the content is intended only for Chinese-speaking users or provide any language/locale opt-in. Under the natural-language policy rule, forcing a specific language without user choice can be a policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file presents all instructional content exclusively in Chinese and does not indicate that other languages are available or that Chinese is a user-selected option. Under the stated policy, a skill that forces a specific language without user opt-in is 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: 89% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that users may choose another language or that the language restriction is deliberate. Under the policy rule for language or locale constraints, forcing a specific language without opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The entire skill content is presented only in Chinese, with no indication that users can choose another language or that the locale restriction is intentional and justified. Under the policy, language constraints should be optional or explicitly documented when region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.