Security audit

QQ每分钟时间提醒

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but it creates a persistent every-minute QQ messaging task with weak safeguards and an hourly-request mismatch.

Review before installing. Only use this skill when you intentionally want a continuing every-minute QQ reminder, confirm the recipient OpenID and Asia/Shanghai timezone, keep the returned task ID, and know how to remove the cron job. Avoid using it for hourly reminders unless the schedule is corrected.

A.I.G

Vulnerability Patterns

System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
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

Findings (2)

T06 · System Persistence

Error

Location: SKILL.md:18
Finding: Persistent High-Frequency Scheduled Message Task
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:16
Finding: Potential Command Injection Through Unvalidated QQ OpenID Substitution
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill instructs the agent to create a persistent cron task that repeatedly sends QQ messages on the user's behalf, but it does not require a clear user-facing warning or confirmation about the ongoing automation. In an agent setting, this can lead to surprise message spam, unintended long-lived tasks, and actions taken without sufficiently informed consent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger guidance is ambiguously scoped: the skill claims to handle both "每分钟提醒时间" and "每小时报时", but the implementation always creates a every-minute cron job. This mismatch can cause unintended activation and creation of a persistent recurring task that sends automated QQ messages more frequently than the user expected.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Hard-coding the timezone to Asia/Shanghai can cause reminders to fire at unexpected times for users in other locales, especially if the skill is reused broadly. While not a direct security exploit, the mismatch increases the risk of unintended automated messaging and user confusion in a persistent scheduling context.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.