Security audit

Feishu Meeting Reminder

Security checks for vulnerabilities and agentic risk

Overview

This Feishu calendar skill is mostly coherent, but it should be reviewed because it includes meeting modification and deletion without documented confirmation safeguards.

Install only if you are comfortable giving the agent Feishu calendar-management authority. Before allowing use, require explicit confirmation for creating, modifying, deleting, or notifying attendees, and verify event details before any destructive action.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger conditions are broad enough to activate on generic requests about meetings, notifications, or creating meetings, which can cause the agent to invoke this skill in contexts the user did not clearly intend. Because the skill exposes creation and management actions for calendar objects, overbroad activation increases the risk of unintended event creation, modification, or other side effects.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The manifest describes a meeting reminder skill focused on automatic reminders, creating schedules with reminders, and viewing upcoming meetings. However, the documented operations also include getting details, patching, deleting, and searching meetings, which makes the skill a broader calendar-management interface rather than a narrowly scoped reminder skill.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The documented interface includes a delete action for meetings without any warning, confirmation requirement, or safety guidance around its destructive nature. In an agent setting, this can lead to accidental deletion of calendar events from ambiguous or mistaken user prompts, causing operational disruption and loss of scheduling information.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: The natural-language instructions, examples, and trigger phrases are all Chinese, and the file does not state that the skill is limited to Chinese-language users or provide an opt-in language choice. This can violate language/locale policy when a skill implicitly forces one language without user selection.

Description-Behavior Mismatch

Low

Confidence: 84% confidence
Finding: The manifest explicitly claims support for setting repeated reminder rules, but the rest of the file documents only a reminders array of minute offsets and does not show any recurrence or repeated-reminder rule parameter. This creates a semantic mismatch between the advertised capability and the actual documented behavior.

Static analysis

No suspicious patterns detected.