Security audit

大圆虾-日程助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple scheduling helper with disclosed reminder, document, and schedule-file actions and no bundled code or install steps.

Before using it for customer or contract schedules, confirm recipients, reminder timing, Feishu document contents, and any schedule-file changes before letting the agent send notifications or write records.

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

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 (1)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly describes use of `message` to send notifications and `write` to create or update schedule records, but it does not instruct the agent to obtain user confirmation before sending messages or modifying files. In a scheduling context, this can cause unintended notifications, accidental record changes, or disclosure of business/customer information through messages or documents.

Static analysis

No suspicious patterns detected.