Back to skill

Security audit

Feishu Suite

Security checks for vulnerabilities and agentic risk

Overview

This Feishu integration requests broad but disclosed workplace permissions for messages, documents, calendars, tasks, and tables, with no hidden code or persistence found.

Install only if you intend to let this skill operate across Feishu messages, documents, calendars, tasks, and bitables. Prefer explicit Feishu-prefixed requests for state-changing actions and review Feishu authorization prompts carefully before approving writes or message sends.

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
94% confidence
Finding

The trigger terms include very broad workplace words such as '文檔/文档', '日程', '任務/任务', and '協作', which are likely to appear in ordinary conversations unrelated to invoking this skill. In a high-privilege enterprise integration that can send messages, modify documents, create calendar events, and manage task/table records, accidental activation could cause unintended actions or expose connected enterprise data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The natural-language description uses mixed simplified and traditional Chinese terms such as "飞书" and "觸發詞:飛書", suggesting a language/locale assumption without stating that users may interact in their preferred language. This can create an implicit locale policy expectation rather than an explicit opt-in choice.

Content

No source excerpt is available for this finding.