ClawHub
Back to skill

Security audit

古董鉴定估价

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent antique appraisal helper with expected photo, provenance, report, and payment-style workflow, but users should be mindful of privacy and payment clarity.

Before installing, treat uploaded photos and provenance as potentially sensitive and avoid sharing personal identifiers, exact addresses, or legally sensitive ownership details. Use the payment flow only when you understand whether it is a demo or a real paid service, and rely on qualified in-person appraisal for high-value, legal, insurance, or transaction decisions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains broad, everyday phrases such as '帮我看看' and '值多少钱', which can cause the skill to activate in unrelated conversations. Because this skill collects images, provenance details, and can initiate payment-oriented flows, accidental invocation increases the risk of unintended data collection, confusing commerce prompts, and misrouting user interactions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill asks users to upload photos and provide provenance/source details, which may contain sensitive personal, location, ownership, or legally sensitive information, but it does not clearly explain how that data will be handled, stored, shared, or retained. In a workflow that also generates orders and payment steps, the lack of a privacy notice meaningfully raises the risk of over-collection and uninformed disclosure.

Static analysis

No suspicious patterns detected.