Back to skill

Security audit

飞书云盘 AI 管家

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu Drive organizer that can move, delete, create folders, search files, and manage comments, with no bundled executable code or hidden behavior found.

Before installing, be aware that this skill can change Feishu Drive content, including bulk moves, folder creation, comment posting, and soft deletion. Use explicit Feishu Drive folder names and review the listed files before approving destructive or bulk actions.

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
  • 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 trigger phrases are broad and include generic file-management terms like '整理文件', '文件夹管理', and '文件分类', which can cause the skill to activate for routine storage-related requests beyond the user's specific intent. Because this skill supports state-changing actions such as move and delete, ambiguous invocation increases the chance of unintended cloud-drive operations on user data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file contains user-facing guidance only in Chinese, and it does not indicate that the language is optional, user-selectable, or limited to a specific audience for a documented reason. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.