ClawHub
Back to skill

Security audit

New House

Security checks for vulnerabilities and agentic risk

Overview

The skill is only a Markdown instruction file and has no executable behavior, but its declared new-house real-estate purpose does not match much of its venue/restaurant-style guidance.

Review before installing because the skill appears mislabeled or poorly scoped: it advertises new-house real-estate help but gives instructions that fit restaurants or venue visits. It does not appear to run code or request sensitive access, but users should expect possible misrouting or inaccurate behavior unless the publisher clarifies the intended domain.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest presents this as a new-house real estate skill, but the body content describes restaurant or venue discovery features such as queue status, electronic ticket numbers, store visits, and consumer spending tiers. This mismatch can cause the agent to route unrelated user requests into the skill or misrepresent the skill’s capabilities, creating a serious trust and prompt-routing integrity issue that could be abused for deceptive behavior or unintended data handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing description and examples are presented only in Chinese, with no indication that the skill supports other languages or that Chinese-only behavior is a justified regional requirement. This can amount to a language/locale policy issue because it implicitly constrains interaction language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example triggers are extremely generic help phrases that can match many ordinary user requests unrelated to this skill. Overbroad invocation language increases the chance of accidental activation, incorrect tool routing, and user confusion, especially when combined with the domain mismatch elsewhere in the file.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.