Smart Nutrition Customizer

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:18 AM UTC
• Version: 1.0.0

Overview

This is a simple meal-planning skill that asks for body data to calculate nutrition targets, with no executable code or persistence, but users should treat its health advice as general guidance.

Install only if you are comfortable sharing basic body and goal information with the agent for calorie and meal-plan estimates. Do not rely on it for medical nutrition therapy, eating-disorder support, pregnancy, minors, diabetes, kidney disease, allergies beyond simple avoidance, or other clinical needs without a qualified professional.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High

• Category: YARA Match
• Confidence: 80% confidence

Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md

---
name: smart-nutrition
description: Smart Nutrition Customizer. Input height, weight, age, gender, and activity level to calculate BMR and macronutrient needs, then generate a full-day meal plan with recipes, calorie counts, and nutrition labels. 
---

# Smart Nutrition Customizer 👩‍🍳

Calculate metabolic rate and nutritional needs from body data, then generate a personalized full-day meal plan.

## Use Cases

Use when the user needs "nutrition planning", "meal plan", "calorie calculation", "weight loss meals", "muscle gain meals", "dietitian", "healthy recipes", or "calorie counting".

## Workflow

### Step

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill's invocation triggers include broad, common phrases such as 'healthy recipes' and 'dietitian', which can cause the skill to activate in contexts where the user did not intend to request personalized nutrition analysis. In this skill, that overreach is more concerning because activation can lead to collection of sensitive health-related data and generation of quasi-medical guidance without clear consent or scope checks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The skill asks for health-related personal data including age, weight, height, gender, activity level, and possibly dietary restrictions or allergies, but provides no privacy notice, consent language, retention guidance, or warning that the output is not medical advice. In context, this increases risk of unnecessary sensitive-data collection and overreliance on automated dietary recommendations, especially for users with medical conditions, eating disorders, pregnancy, or age-related vulnerabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The instruction "Chinese cuisine first" imposes a default locale/cultural preference on outputs even if the user has not requested it. This is a natural-language policy concern because the file does not offer an explicit user choice or justify the locale restriction as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.