Back to skill

Security audit

Weight Management 体重管理

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent weight-management assistant, but it asks for broad chat-history access and stores sensitive health records with under-specified file/path controls.

Review this skill carefully before installing. It appears intended for local weight tracking and does not ship suspicious executable code, but you should avoid granting broad chat-history access unless you need historical import, use a dedicated storage folder, and avoid putting your real name in filenames until the privacy statement and path-validation rules are fixed.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:29
Finding

Excessive Chat-History Permission for Health Data Processing

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:278
Finding

Unsanitized User-Controlled Components in Archive Paths

Content
View full analysis
Remediation
View remediation
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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明描述的是一个较完整的减肥管理与数据分析技能,涉及记录管理、文件命名规范、数据检查、饮食热量识别和趋势分析等多项能力;而提供的代码只是一个独立的 CLI 计算器,使用标准公式计算 BMR/TDEE,并给出固定的热量建议。虽然 TDEE 计算与减肥领域相关,属于声明场景中的一个支持性子功能,但不足以覆盖声明中的核心能力,且代码完全没有实现所宣称的大部分功能。因此描述与实际行为存在明显的实质性不匹配。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad, everyday phrases such as meal-related words that could activate the skill unintentionally during normal conversation. In a skill with file read/write and session access, unintended activation can lead to unwanted data capture, archival, or analysis of sensitive health information without clear user intent.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The document states that it does not collect usernames or other identity information, but later requires a username and persists it in filenames. This is dangerous because users may consent under false privacy expectations, and filenames can expose personal identifiers through directory listings, backups, logs, and screenshots.

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 is entirely written in Chinese and presents itself as a general-purpose calorie reference for a weight-loss management skill, with no indication that the user opted into Chinese or that the skill is region-specific. That creates a natural-language policy issue because it effectively imposes a specific language on users without documented choice or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language strings throughout the script, including the module docstring, CLI help text, and printed results, are all hard-coded in Chinese. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in, and this file provides no language selection or justification for being Chinese-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is entirely written in Chinese and includes user-facing registration and confirmation text, but it does not offer any opt-in or alternative language choice. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale/language policy issue unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language description and invocation examples are entirely in Chinese, with no indication that users may interact in other languages or choose their preferred locale. Under the policy, a skill should not implicitly force a specific language unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This requirements file includes prominent Chinese-language comments alongside English, naming the skill as a Chinese-language weight-management skill, but it does not state that language choice is optional or region-specific. Under the natural-language policy rule, language constraints should be explicitly optional or justified to avoid implying a forced locale.

Content

No source excerpt is available for this finding.