Back to skill

Security audit

飞书Bitable管理工具

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent Feishu Bitable helper for managing tables, records, fields, views, and attachments, with no hidden code or local persistence found.

Install only if you intend the agent to manage Feishu Bitable data. Before writes, deletes, batch operations, schema changes, or attachment uploads, confirm the exact app_token, table_id, records, fields, and file contents, because those actions can persist business data changes in Feishu and deletions may not be recoverable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The examples explicitly demonstrate destructive actions such as deleting records and batch modifying data, but they do not clearly require confirmation of the target app/table/records before execution. In a data-management skill, this omission can lead to accidental deletion or corruption of production data if an agent or user applies the example flow to the wrong table or stale record set.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The attachment workflow shows how to upload and store files in Bitable but does not warn that uploaded content may contain sensitive personal, contractual, or business data and will be persisted in Feishu storage. In this skill context, users are likely handling customer and contract records, so missing privacy and data-classification guidance increases the risk of unintended disclosure or policy violations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document states that writing a new single-select option name will automatically create a new schema option, but it does not warn that this changes table schema rather than just record data. In an agent setting, unvalidated user input could silently proliferate options, corrupt controlled vocabularies, break downstream automations/filters, and create persistent data integrity issues.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The multi-select section likewise documents automatic creation of previously unseen options without warning that this is a schema-changing side effect. In this skill context, batch imports and bulk updates make the risk higher because typos or prompt-injected values can create many persistent labels at once, degrading data quality and potentially affecting reporting, permissions workflows, or integrations that depend on fixed taxonomies.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

SQP-3 适用于所有文件类型。该文件从标题到全部操作说明均仅以中文提供,未给出多语言选项、未说明这是面向特定中文环境的限定文档;若该技能用于通用用户群,可能构成未经用户选择的语言约束。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

该 markdown 文件从标题到正文均仅使用中文,没有提供其他语言选项,也没有说明该技能或文档为何必须限定为中文。根据语言/地区策略,这属于未提供用户选择的语言约束。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The title and entire document are written only in Chinese, and the examples explicitly use the Chinese locale zh-CN and Beijing/Shanghai timezone conventions. For SQP-3, this is a natural-language locale preference that is presented as the default without any opt-in or statement that the skill is region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.