ClawHub
Back to skill

Security audit

What To Eat

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives random meal suggestions from built-in restaurant lists and does not request sensitive access or execute code.

Before installing, understand that this is a lightweight Chinese meal-picker skill with fixed local restaurant data; the main improvement would be narrowing the trigger wording so it activates only for meal-choice 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
  • 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
96% confidence
Finding

The metadata says the skill may trigger on 'any food-related questions,' which is broader than the concrete trigger list in the body and could cause unintended activation for general food discussions rather than explicit recommendation requests. This is not a code-execution issue, but it can lead to scope overreach, incorrect routing, and user confusion if the assistant invokes the skill in contexts where it was not intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The file presents the skill as Chinese-language in its title and trigger examples, while the top-level description is in English, but nowhere states whether responses are forced to Chinese or lets the user choose language. For organizational language-policy review, this can create an implicit locale/language constraint without explicit opt-in.

Content

No source excerpt is available for this finding.