Security audit

Popeye Health

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown wellness skill with no code execution or persistence, but users should treat its health guidance as general information only.

Install only if you are comfortable using a Chinese-language wellness assistant and sharing limited health-related context with your agent. Treat its exercise, diet, and sleep suggestions as general wellness guidance; consult a qualified clinician or dietitian for injuries, chronic conditions, pregnancy, medication interactions, eating-disorder history, severe insomnia, or other medical concerns.

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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This skill provides exercise, nutrition, and sleep guidance but does not warn users that the content is not medical advice, does not instruct users to consult a clinician for conditions or symptoms, and does not acknowledge that users may disclose sensitive health information. In a health-related context, that omission can lead users to rely on potentially unsafe guidance or overshare personal health data without clear expectations about risk and privacy.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module provides concrete nutrition targets and meal recommendations without warning users that the guidance is general information and may be inappropriate for people with medical conditions, allergies, eating disorders, pregnancy, kidney disease, diabetes, or other special dietary needs. In a health-focused skill, users may over-trust the advice and follow it as personalized guidance, increasing the risk of harm from unsuitable calorie, macro, or food choices.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file presents all instructions, examples, and output format exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description, headings, trigger phrases, examples, and usage instructions are all presented only in Chinese, with no indication that other languages are supported or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user 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: 93% confidence
Finding: The natural-language instructions, examples, and output format are all written in Chinese, which effectively forces a specific language for interaction. The file does not offer user opt-in, alternative language support, or a documented reason for restricting the skill to this locale.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.