ClawHub
Back to skill

Security audit

weekday-meal-decider

Security checks for vulnerabilities and agentic risk

Overview

This meal-planning skill is coherent and disclosed, with the main consideration being that it sends food preferences and dietary constraints to an external recipe API.

Install this if you are comfortable with food preferences, ingredients, intolerances, and diet constraints being sent to AirnodeHub Spoonacular for recipe lookup. Review the broad food-related trigger if you only want the skill used on explicit meal-planning requests.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill’s trigger scope is very broad, covering generic requests about food, dinner choices, and what to cook or eat. That can cause the skill to activate for many ordinary conversations and autonomously steer users into external API-backed behavior, increasing the chance of unintended tool use and over-collection of user preferences or dietary data.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Verification

Before replying, confirm that recipe discovery and detail retrieval used POST, every recommendation respects the stated time, diet, intolerances, exclusions, servings, and equipment, factual details came from the attested `data` response, and no paid or credentialed action occurred without approval.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.