Back to skill

Security audit

飞书会议纪要AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Feishu meeting-minutes helper, but users should be aware it can read meeting sources and send generated minutes in Feishu.

Install only if you are comfortable granting the agent access to the Feishu meeting sources you provide or ask it to summarize. Before using automatic distribution, confirm the target document, group chat, and recipients so confidential meeting content is not shared more broadly than intended.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill name, description, triggers, and output template are written to operate in Chinese by default, including the invocation example and output headings. There is no indication that users may choose another language or that the Chinese-only behavior is a documented, justified regional constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is designed to access potentially sensitive Feishu documents, chat discussions, and tables, and it also states it can automatically send generated minutes to participants, but it does not warn users about that data access or outbound sharing behavior. This can lead to unintentional exposure of confidential meeting content, participant identities, action items, or internal decisions if users invoke the skill without understanding the scope of collection and redistribution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.