Back to skill

Security audit

bitable-formula-generator

Security checks for vulnerabilities and agentic risk

Overview

The skill openly helps generate and optionally write Feishu Bitable formula fields, using Feishu API credentials supplied through environment variables.

Install only if you intend to let the agent use Feishu Bitable app credentials to inspect table schema and create or update formula fields. Use a least-privileged Feishu app, test formula changes on a duplicate table when possible, and explicitly review any set-formula or direct PUT/POST operation before running it against production data.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (18)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented behavior materially exceeds the stated purpose: instead of only helping generate formulas from exported Excel structure, it also retrieves Feishu app credentials, enumerates tables and fields, inspects field properties, and directly creates or updates formula fields. This mismatch can mislead users and orchestrators into granting trust to what appears to be a local formula helper while it actually has live remote read/write capabilities against production data structures.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 109)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 268)May include surrounding context.

md
1. **API 自动获取(推荐)**:使用 `scripts/feishu-bitable-api.js` 脚本自动列出表和字段。

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/feishu-bitable-api.js (reported line 127)May include surrounding context.

js
});
}

// ==================== 获取 Access Token ====================

/**
 * 从飞书获取 tenant_access_token 并存入 global.accessToken。

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/feishu-bitable-api.js (reported line 151)May include surrounding context.

js
});
}

// ==================== 获取 Access Token ====================

/**
 * 从飞书获取 tenant_access_token 并存入 global.accessToken。

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill documents use of environment-based Feishu credentials and API-capable scripts, but it does not declare any explicit tool scope or permission boundary. That creates an overprivileged, under-specified execution model where an agent may access secrets or perform actions beyond what a user reasonably expects from a formula-generation skill.

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 direct PUT/POST-style writes that can create or modify live formula fields, but it does not prominently require explicit user acknowledgement that production table schema will be changed. In context, this is more dangerous because formula-field updates can silently alter downstream calculations, dashboards, and business logic across an active Bitable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest description presents the skill entirely in Chinese with no indication that users may interact in other languages or choose their preferred locale. This can be a language policy issue when a skill implicitly forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, beginning with the title and continuing throughout the reference tables. Under the policy rule, forcing a specific language without opt-in can be a locale/language policy violation when no alternative or justification is provided.

Content

No source excerpt is available for this finding.