Back to skill

Security audit

飞书文档 AI 写作助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Feishu document-writing helper with disclosed document creation and formatting behavior, though users should be careful with bulk edits.

Install only if you want the agent to create and edit Feishu documents. For replacements or batch document generation, confirm the target documents and review the intended changes before letting the agent proceed.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises automatic document creation, formatting, batch generation, and content replacement, but does not clearly warn users that invoking it can cause immediate write actions in Feishu. This increases the risk of unintended document creation or mass modification, especially when triggered from natural-language requests that users may perceive as advisory rather than operational.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example triggers use broad, everyday phrases such as asking for a weekly report or meeting notes, without defining strict activation boundaries, confirmation requirements, or exclusions. In an agent environment, this can cause the skill to activate on routine conversation and perform unintended write actions to Feishu documents, making accidental misuse more likely.

Content

No source excerpt is available for this finding.