Back to skill

Security audit

feishu-cron-reminder

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Feishu reminder helper, but its shell-command templates and broad reminder activation create review-worthy risk for accidental outbound messages and command injection.

Review before installing. This skill should only be used when you want reminders delivered through Feishu, and agents should confirm the recipient, schedule, timezone, and exact message before creating any job. Do not let an agent build and run these examples as raw shell strings with untrusted reminder text; use structured argument passing or robust escaping, especially for messages, names, descriptions, and destination IDs.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:26
Finding

Shell Command Injection Through Unescaped Reminder Content

Content
View full analysis
Remediation
View remediation
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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README states 'AI 默认使用北京时间(Asia/Shanghai)', which imposes a specific locale/timezone behavior. Under the policy, forcing a locale without user opt-in is a natural-language policy violation unless the constraint is clearly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation guidance is broad enough that common reminder phrases like '提醒我明天9点开会' may trigger this Feishu-specific skill even when a user only wants a generic reminder, causing unintended creation of scheduled tasks and delivery to Feishu recipients. In a scheduling/integration skill, over-broad activation increases the chance of scope confusion, accidental outbound messaging, and misuse of previously configured recipient IDs or defaults.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest text is entirely in Chinese and presents the skill's functionality only in that language, which can constitute a language/locale policy violation when no user opt-in or alternative language is offered. Nothing in the manifest indicates that the skill is region-specific or intentionally limited to Chinese-speaking users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

This markdown file instructs users to create scheduled tasks that automatically push messages to Feishu recipients. While the README explains that reminders can be recurring, it lacks a clear user-facing warning that these automations will continue sending messages until manually removed and may affect group chats or create notification spam if configured incorrectly.

Content

No source excerpt is available for this finding.