ClawHub
Back to skill

Security audit

Home Cook

Security checks for vulnerabilities and agentic risk

Overview

This is a simple home-cooking reference skill with no code execution, credential use, persistence, or hidden behavior.

This skill appears safe to install for ordinary cooking help. Users should treat it as general kitchen guidance and use extra care for allergies, medical diets, or food-safety-critical situations.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broad enough to trigger on very common, everyday cooking-related requests, which increases the chance of over-activation and unintended routing. While not an exploit in the traditional sense, excessive scope can cause the agent to invoke this skill in contexts where a narrower or more appropriate skill should handle the request, degrading safety and policy enforcement through misclassification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'When to Use' section lists generic activation criteria without guardrails, negative examples, or disambiguation rules, making the skill eligible for a wide range of loosely related prompts. This broad matching can lead to unnecessary invocation and create routing ambiguity with other skills, which is a security-relevant quality issue because it expands the skill's effective authority surface.

Content

No source excerpt is available for this finding.