Back to skill

Security audit

fitatu-diary

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Fitatu account access and diary changes fit its stated purpose, with disclosed session storage and clear controls over changes.

This unofficial integration can read sensitive health information and change your Fitatu diary. Use --read-only if you only want reports, protect the saved session and remote-access token, and make clear when nutrition discussions should use your account. Changes inferred beyond your request require confirmation.

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
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 (1)

Activation includes generic mentions of food, weight, or water without requiring a Fitatu diary context.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The activation description includes generic references to food, weight, water, and calorie goals without requiring a Fitatu context, so unrelated nutrition discussions could activate an account-connected diary workflow. This can lead to unnecessary access to sensitive health data or inappropriate diary actions, although the requirement for a direct request or confirmation before changes substantially limits the risk. The content shows overly broad routing rather than evidence of malicious intent.

Content

No source excerpt is available for this finding.