ClawHub
Back to skill

Security audit

Feishu Bitable CRUD

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Feishu Bitable CRUD helper; it can change live Bitable data, but that capability matches its stated purpose and no hidden or deceptive behavior was found.

Install only if you intend your agent to modify Feishu Bitable data. Use a Feishu app with the narrowest practical permissions and confirm the target base, table, record, and fields before asking the agent to create or update records.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Session Persistence

Medium
Category
Rogue Agent
Content
Feishu/Lark Bitable CRUD skill. Teaches your agent to correctly use feishu_bitable_* tools
  for creating, reading, updating records in Feishu Bitable. Handles both /wiki/ and /base/ URL
  formats automatically — resolves wiki node_token to real bitable app_token before any operation.
  Use when: agent needs to read/write Feishu Bitable (multidimensional spreadsheet) data.
metadata:
  clawdbot:
    emoji: "📊"
Confidence
72% confidence
Finding
The skill is designed to read and write persistent data in an external Feishu Bitable instance, which means agent actions can have durable side effects beyond the current session. While persistence is the purpose of the skill, the lack of accompanying constraints around authorization, confirmation, and scope verification makes this capability security-relevant because mistakes or prompt-manipulated actions can permanently alter user data.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly instructs the agent how to create and update Feishu Bitable records but does not include any guardrails such as requiring explicit user confirmation before mutating existing data, warning that operations affect live remote records, or encouraging read/list validation before writes. In an agent setting, this increases the risk of unintended modification of production data if the agent misinterprets the user's request or targets the wrong table after token resolution.

Static analysis

No suspicious patterns detected.