Security audit

Feishu User Doc

Security checks for vulnerabilities and agentic risk

Overview

This skill is simple and disclosed, but it creates Feishu documents under a named user's account without clear authorization or confirmation guardrails.

Install only if users are expected and authorized to create documents as 韩博. Before use, confirm the account context and document title, and avoid enabling this where other users could accidentally or intentionally create documents under that identity.

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

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill description states that documents will be created directly under 韩博's ownership but does not present this as a user-facing warning or require informed consent. Because the skill performs actions as a specific user's account (--as user), omission of a clear warning can mislead operators or requesters into triggering identity-bound actions with ownership, attribution, and audit consequences.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrase '直接告诉我「创建飞书文档 xxx」' is broad and does not constrain who may request document creation, what content is permitted, or whether explicit confirmation is required before acting as a specific user account. In this context, the skill is designed to create documents under 韩博's identity, so an overly permissive activation condition increases the risk of unauthorized or accidental actions under that account.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The skill description and invocation guidance are entirely in Chinese and instruct the user to say a Chinese phrase, with no indication that other languages are supported or that Chinese is a justified requirement. This can violate language/locale policy when a skill implicitly forces one language without user opt-in.
Content: No source excerpt is available for this finding.