Security audit

周报月报生成

Security checks for vulnerabilities and agentic risk

Overview

This report-writing skill is broadly aligned with its purpose, but it needs review because it can expose chat content to Feishu-style documents without clear per-use consent and may claim document creation without a real integration.

Review carefully before installing. Use it only with explicit requests, check generated reports before sharing, avoid including sensitive chat history unless needed, and verify any Feishu integration creates a real document in the intended workspace with limited permissions and known recipients.

SkillSpector

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)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases include broad everyday expressions such as '月报', '项目报告', and '会议纪要', which can plausibly appear in normal conversation outside an explicit request to invoke this skill. That increases the chance of unintended activation, which is especially risky here because the skill can read recent conversation history and create or update Feishu documents and send IM notifications.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill description states it reads recent conversation history and uses Feishu document/IM integrations, but it does not clearly disclose these data accesses and external writes to the user at invocation time. This creates a privacy and consent risk: users may unknowingly have prior conversation content extracted and pushed into external systems, potentially exposing sensitive business information.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The handler automatically creates a Feishu document when configuration enables it and a user ID is present, but the code provides no prior notice, consent flow, or clear disclosure that user content will be sent to an external document system. This can lead to unintended data sharing or persistence of sensitive report contents in a third-party workspace, especially if users expect only an inline response.

Static analysis

No suspicious patterns detected.