ClawHub
Back to skill

Security audit

通联终端申请 & 增商

Security checks for vulnerabilities and agentic risk

Overview

This skill appears benign because it transparently automates a Tonglian terminal and sub-merchant application workflow, with user confirmation required before sending email.

Install this only if you intend to use it for Tonglian terminal or sub-merchant onboarding. Review generated forms and email text carefully before saying "发", because the workflow handles merchant data and can send application materials to an external payment contact.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger conditions for terminal application are broad enough to match common conversational requests such as '申请终端' or 'POS机申请' without stronger scoping to the specific Tonglian workflow. This can cause the agent to invoke a high-impact business process in the wrong context, leading to collection of merchant data, generation of official forms, and preparation of outbound email for an unintended request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The sub-merchant onboarding triggers rely on short ambiguous phrases like '增商', '新增商户', and '子商户', which may appear in unrelated business discussions. In this skill, accidental activation is more dangerous because the workflow creates onboarding artifacts and instructs sending them to an external payment contact, increasing the chance of unauthorized or erroneous merchant changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill is entirely written as a Chinese-only workflow with fixed Chinese trigger phrases and templates, but it does not indicate that language choice is optional or user-selectable. This can violate a language/locale policy when a skill implicitly forces one language without opt-in or documented justification.

Content

No source excerpt is available for this finding.