Back to skill

Security audit

通联VIP对账单配置

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed internal workflow for creating and sending VIP reconciliation configuration spreadsheets, with no hidden code, persistence, or unrelated behavior found.

Before installing, users should be aware that this skill processes merchant, store, and terminal identifiers and can send the generated spreadsheet to a named internal contact and create a Feishu task. Confirm the file contents, recipient, and task details before approving delivery.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 phrases are very broad business terms like '配置对账单' and 'VIP配置', which can plausibly appear in ordinary discussion and cause unintended activation. Because this skill initiates a workflow involving financial configuration data and downstream messaging/task creation, accidental invocation could lead to premature collection or handling of sensitive merchant information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to send a generated file containing merchant and terminal identifiers to another person and create a task, but it does not require explicit user authorization for external sharing at the point of transfer. Even though it includes an initial user confirmation of the file contents, that is not the same as a clear consent checkpoint for sharing potentially sensitive business data with named third parties.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The instruction “纯英文,不要中文” imposes a language constraint on output format. The file does not explain why this restriction is necessary or provide an opt-in or alternative, which can conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.