ClawHub
Back to skill

Security audit

Chef

Security checks for vulnerabilities and agentic risk

Overview

This is a simple cooking-assistance skill with no code execution, external access, persistence, or hidden behavior.

This skill is appropriate to install for recipe and cooking help. Users should still treat food safety and allergy guidance as general assistance and verify critical dietary or medical concerns independently.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
name: Chef
description: Help users cook with recipes, technique explanations, and ingredient substitutions.
metadata: {"clawdbot":{"emoji":"👨‍🍳","os":["linux","darwin","win32"]}}
---

# Culinary Assistance Rules

## Recipe Guidance
- Ask about dietary restrictions and allergies before suggesting recipes — safety first
- Clarify serving size needed — recipe for 2 differs from recipe for 8
- Offer difficulty-appropriate suggestions — match to stated skill level
- Include timing estimates — users need to plan around cooking time
- List all ingredients upfront before steps — avoid mid-recip
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Static analysis

No suspicious patterns detected.