ClawHub
Back to skill

Security audit

Nutrition Planner

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a straightforward nutrition-planning skill, but it stores health-related profile details locally and the packaged command it documents is missing from the artifact.

Use this only on a device where you are comfortable storing nutrition and health-adjacent details such as allergies, weight, goals, and dietary restrictions. Check ~/.openclaw/data/nutrition-planner/ and delete the database when no longer needed. Also note that this package appears incomplete because the documented nutrition-planner executable is not present in the artifact.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
93% confidence
Finding

The documentation instructs users to create and store profiles containing personal and health-related data such as age, weight, height, dietary restrictions, and allergies, and states that this data is persisted in a local SQLite database. There is no warning about the sensitivity of this information, retention, local-user exposure, backups, or device compromise, which can lead users to handle regulated or sensitive data insecurely.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The duplicated finding identifies the same persistent-profile behavior: the skill stores named nutrition profiles that can include age, body metrics, restrictions, and allergies. In a nutrition-planning context this makes the persistence more sensitive than generic app state, because it concerns health-adjacent personal data and could expose users if the local machine, account, or backups are accessed.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

bash
# 基础档案
${SKILL_DIR}/scripts/nutrition-planner profile-create \
  --name "张三" \
  --age 30 \
  --gender male \

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The duplicated finding identifies the same persistent-profile behavior: the skill stores named nutrition profiles that can include age, body metrics, restrictions, and allergies. In a nutrition-planning context this makes the persistence more sensitive than generic app state, because it concerns health-adjacent personal data and could expose users if the local machine, account, or backups are accessed.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

bash
# 基础档案
${SKILL_DIR}/scripts/nutrition-planner profile-create \
  --name "张三" \
  --age 30 \
  --gender male \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill collects and stores sensitive personal profile data, including age, weight, height, dietary restrictions, allergies, and fitness goals, and explicitly documents local persistence in a predictable path. Omitting a privacy warning can mislead users into entering health-related data without understanding retention or local exposure risks, especially on shared or unmanaged systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The user-facing instructions and feature descriptions are presented in Chinese, while the file does not indicate that the skill is region-specific or provide an opt-in or alternative language. This can violate language/locale policy when a skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.