Back to skill

Security audit

网页搜索整理到飞书多维表格知识库

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed automation for searching the web and saving summarized results into a user's Feishu Bitable knowledge base.

Before installing, be aware that this skill can create Feishu Bitable apps/tables and batch-add records using your authorized Feishu account. Confirm the destination Bitable and fields when using it, especially if you already have an existing knowledge base.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description emphasizes automation but does not clearly warn that the skill may create a new Feishu Bitable app or append records to an existing one. This is dangerous because users may believe they are only performing search/collection, while the skill actually persists data and modifies external state in their Feishu environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation phrases are broad enough that ordinary user requests to search for information and organize it into Feishu could trigger the skill without a clear confirmation boundary. Because this skill performs downstream write actions to Feishu, overbroad activation increases the chance of unintended data creation or modification in a user-owned workspace.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

All user-facing instructions, examples, and invocation phrases are presented only in Chinese, and the skill does not indicate that language selection is optional or region-specific. This can be a natural-language policy issue when a skill implicitly forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.