Security audit

Weight Loss Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable weight-loss planning skill, but its health guidance contains concrete calculation and exercise-safety defects that users should review before installing.

Review and correct the nutrition formulas and meal totals before use. Install only for users who can understand the Chinese instructions, and add explicit confirmation, medical-risk screening, safer substitutions, and clear stop or clinician-referral conditions before generating plans.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (3)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:48
Finding: Reversed Mifflin–St Jeor Sex Constants Produce Incorrect Calorie Prescriptions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: references/meal-plans.md:102
Finding: Meal Templates Understate Breakfast and Daily Calorie Totals
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: references/exercise-plans.md:61
Finding: Fixed High Heart-Rate Targets Can Produce Unsafe Exercise Guidance
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger scope is broad enough to activate on many general health, diet, fitness, calorie, or BMI-related conversations, which can cause the skill to run when the user did not explicitly ask for a weight-loss plan. In this context, unintended activation is riskier because the skill produces personalized health guidance, so over-triggering can lead to unsolicited or misapplied medical-adjacent recommendations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill description is written to operate in Chinese without indicating language negotiation or fallback behavior, which can cause users to receive safety-critical health instructions in a language they may not fully understand. In a health-planning context, language mismatch increases the chance of misunderstanding calorie limits, contraindications, or warning notices.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This exercise library includes advanced and potentially injury-prone content such as HIIT, sprint intervals, jump squats, box jumps, weighted movements, and progression cues, but it does not consistently require pre-screening for medical conditions, injury history, pregnancy, medication effects, cardiovascular risk, or explicit stop/seek-care guidance. In a weight-loss planning skill, users may directly operationalize these plans as personalized advice, so missing safety gating materially increases the risk of overexertion, falls, joint injury, or adverse cardiac events for vulnerable users.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file provides prescriptive calorie-restricted meal plans tied to sex, body size, and weight-loss goals, but it does not warn users that the guidance is general informational content rather than individualized medical or nutritional advice. In the context of a weight-loss planning skill, this increases the risk that users with medical conditions, eating disorders, pregnancy, adolescence, or atypical energy needs may follow unsuitable diets and suffer harm.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: SQP-3 适用于所有文件类型。该文件全部以中文呈现，未说明这是面向特定中文用户群的限定内容，也未提供其他语言或用户选择语言的方式；若组织要求技能不应默认强制单一语言，这构成潜在的自然语言策略问题。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: All headings and instructions are written in Chinese, and the file does not indicate that the skill is region-specific or that users may opt into this locale. Under the policy rule for language/locale, a skill should not implicitly force a specific language unless it offers a choice or clearly documents a justified constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.