ClawHub
Back to skill

Security audit

FoodLens

Security checks across malware telemetry and agentic risk

Overview

FoodLens has a coherent meal-photo tracking purpose, but it sends personal food images to external AI services and stores diet logs while relying on unbundled local code and missing clear consent or deletion controls.

Install only if you are comfortable with meal photos being processed by the configured AI provider and nutrition history being saved locally. Review or obtain the missing Python files before use, and decide how you will delete or manage the stored daily JSON logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly persists meal-analysis results in local daily JSON logs, but it does not warn users that their nutrition records are being stored. Meal photos and diet logs can reveal sensitive health, religious, and lifestyle information, so silent retention creates a privacy and consent problem. In this context, the skill is specifically designed to process personal health-adjacent data, which makes undisclosed storage more sensitive than ordinary application logging.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The fallback path sends meal photos to external vision services, but the skill does not require notifying the user or obtaining consent before transmitting the image off-device. Food photos may contain sensitive contextual data such as location, routines, health conditions, or other visible personal information, so undisclosed third-party sharing is a real privacy risk. Because this skill is triggered by user meal photos, the likelihood of handling personal data is high, increasing the severity of missing disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.