Back to skill

Security audit

健身训练计划台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple fitness-plan writing skill with clear safety boundaries and no evidence of hidden access, code execution, data exfiltration, or persistence.

This appears safe to install for generating workout-plan drafts. Users should treat it as general fitness guidance, avoid sharing unnecessary sensitive health details, and consult a qualified professional for injuries, cardiovascular conditions, post-surgery training, or medical concerns.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing metadata, triggers, and instructions are written only in Chinese, and the skill does not indicate that users may choose another language. Under the stated policy, a language-specific constraint should either be optional for the user or clearly justified as region- or locale-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The listed trigger phrases such as “健身计划”, “居家健身”, and “训练安排” are generic requests that could appear in ordinary conversation, making unintended activation more likely. The file does not provide narrowing conditions, exclusions, or negative examples that clarify when the skill should and should not activate.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L03、L26 和 L74 明确将“训练记录表”列为该技能的标准输出内容,但 L69 又称“记录表”属于增强能力,仅在 Pro 版本提供。这不是简单遗漏,而是同一文档内对该技能是否提供记录表能力的直接冲突,导致开发者意图表述不一致。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.