ClawHub
Back to skill

Security audit

Nutrition Logger Pro

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local nutrition logging skill that stores meal records on disk and does not show hidden network access, credential use, or deceptive behavior.

Install only if you are comfortable keeping a local meal history on disk. Configure the log directory deliberately, avoid shared or synced folders if privacy matters, and use explicit logging commands to reduce accidental entries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to read files, write persistent local logs, inspect environment variables, and execute a Python CLI, yet no explicit permissions are declared. This creates a capability/consent mismatch: a caller or platform reviewer may believe the skill is low-risk while it can persist user data and invoke shell-backed operations, increasing the chance of unauthorized file access or unintended data retention.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The top-level description and examples include very common phrases such as '记录', '早餐', '午餐', and '晚餐', which can appear in ordinary conversation unrelated to logging. Broad triggers raise the risk of accidental invocation and unintended storage or modification of sensitive dietary data, especially because this skill maintains persistent local logs.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The dedicated trigger list repeats ambiguous standalone phrases in both Chinese and English without strong scope constraints. Because the skill can append entries, summarize history, undo, and update records, an overly permissive matcher can cause unintended data writes or destructive actions from routine chat text.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill body states that it '维护本地持久日志' and later describes default log directories, but the user-facing description does not clearly disclose persistent local storage behavior. Users may provide sensitive health-adjacent dietary information without understanding that it will be retained on disk, which is a transparency and privacy problem.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.