ClawHub
Back to skill

Security audit

recipe-finder

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps look up recipes from a public recipe API and does not show hidden, persistent, or destructive behavior.

Before installing, understand that recipe-related prompts may be sent to TheMealDB for lookup; avoid including sensitive personal information in meal requests if you do not want it sent to that public API.

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
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad, everyday requests such as asking for dinner recipes or meal ideas, which can cause the skill to activate in situations where the user did not explicitly intend to use this specific integration. That can lead to unnecessary external API calls, irrelevant responses, or unintended handling of user input, even though the skill itself is otherwise low risk and uses a public recipe API.

Static analysis

No suspicious patterns detected.