Back to skill

Security audit

飞书文档翻译助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward Feishu document translator with disclosed read/write behavior, though users should confirm which document is read and where translated content is written.

Before using it, make sure the source Feishu document is intended for translation and that the destination is correct, especially for confidential documents or requests that append translated text to an existing document.

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
90% confidence
Finding

The trigger list includes broad phrases such as '文档翻译', '中英互译', and '双语文档', which can match many generic user requests without making clear that this skill will operate on Feishu documents using read/write capabilities. Overly broad activation increases the chance the skill is selected in contexts where the user did not intend document access, causing unnecessary exposure or modification of document data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill clearly states it can read full Feishu documents and create or write translated output, but it does not prominently warn users that existing document contents will be accessed and copied into new or existing documents. This can lead to unintended disclosure, duplication of sensitive business content, or accidental modification when users invoke the skill without understanding its data access and write behavior.

Content

No source excerpt is available for this finding.