Fiber Fueled: The Plant-Based Gut Health Program for Losing Weight, Restoring Your Health, and Optimizing Your Microbiome

Security checks across malware telemetry and agentic risk

Overview

This looks like a nutrition guidance skill rather than malware, but it needs review because it can give medical-adjacent diet advice for chronic conditions without clear safety limits.

Review before installing. Treat the skill as general educational nutrition content only, not medical advice. Users with diagnosed GI disease, diabetes, autoimmune or thyroid conditions, pregnancy, eating-disorder history, medication use, severe symptoms, bleeding, fever, weight loss, or persistent pain should consult a qualified clinician before following dietary changes. The publisher should narrow activation triggers and add clear medical-safety disclaimers and escalation guidance.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The trigger list is excessively broad and includes many generic health, diet, and disease-related phrases such as IBS, diabetes, autoimmune, and common food terms. This can cause the skill to activate outside clear user intent, leading to unsolicited health guidance being inserted into conversations where the user did not explicitly request this skill, increasing the risk of misleading or inappropriate medical-adjacent advice.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The condition that the skill should trigger when a user says they just installed it or does not know how to start is ambiguous and instructs the AI to proactively present content without waiting for consent. In a health-oriented skill, forced unsolicited activation increases the chance of injecting medical or nutrition advice into unrelated onboarding flows and reduces user control.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
This skill provides health and nutrition guidance touching on conditions like IBS, IBD, Crohn's, ulcerative colitis, SIBO, diabetes, autoimmune disease, and thyroid issues, but it lacks a clear warning that the content is informational and not a substitute for professional medical advice. In this context, users may over-trust the guidance for symptom management or disease treatment, creating a realistic risk of harm from delayed care or inappropriate self-management.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The file presents a structured 4-week dietary program alongside strong health outcome claims, including reversal or improvement of conditions such as diabetes and thyroid-related issues, without advising users to seek medical guidance. In a skill explicitly triggered by users asking about IBS, diabetes, autoimmune disease, IBD, and other health conditions, this omission can lead users to change diet or medications without appropriate clinical supervision.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
This file provides broad health and dietary guidance for gastrointestinal symptoms and chronic-condition-adjacent topics without any warning that it is educational only, not personalized medical advice, and not appropriate for all users. Because the surrounding skill is designed to trigger on users mentioning IBS, IBD, Crohn's, ulcerative colitis, diabetes, and similar conditions, users may over-trust generalized claims such as reintroducing foods or interpreting gas/bloating as normal adaptation, which could delay appropriate medical evaluation or worsen symptoms in some cases.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal