ClawHub
Back to skill

Security audit

兔兔生活（爱佳肴 Love Life）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed restaurant search and publishing helper for tutulife.cn, with write actions gated on user consent.

Install only if you want your agent to use tutulife.cn for restaurant search and, with your permission, publish restaurant details or feedback publicly. Do not put personal identity details in search queries, and keep any returned agent_key in secure local storage rather than chat logs or public files.

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
95% confidence
Finding

The publishing triggers include underspecified commands like '把我的店发布出去', '让 AI 推荐我的店', and '去反馈一下', which can match unrelated marketing or feedback intents outside this service. In context, this is more dangerous because the skill supports account-like registration, agent_key creation, and public posting of business data, so an accidental match could lead to unintended external publication or credential generation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The publishing triggers include underspecified commands like '把我的店发布出去', '让 AI 推荐我的店', and '去反馈一下', which can match unrelated marketing or feedback intents outside this service. In context, this is more dangerous because the skill supports account-like registration, agent_key creation, and public posting of business data, so an accidental match could lead to unintended external publication or credential generation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.