ClawHub
Back to skill

Security audit

定时提醒工具(免费版)

Security checks for vulnerabilities and agentic risk

Overview

This timer skill mostly describes a normal local reminder tool, but it also asks to be used for unrelated writing and marketing tasks while requiring command execution and background process control.

Review this before installing. It should only be used when you explicitly want timers, reminders, or pomodoro sessions. Avoid letting it route writing, marketing, or title-generation prompts, and be careful with background timers and any command that terminates a running session.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (3)

Vague Triggers

High
Confidence
91% confidence
Finding
The manifest advertises a timer tool but also claims applicability to broad writing and marketing tasks, which can cause the agent to invoke an exec-capable skill in contexts unrelated to timing. Overbroad routing is dangerous because this skill has read/write/exec permissions and background-process behavior, so accidental selection increases the chance of unnecessary command execution or process manipulation on the host.

Vague Triggers

High
Confidence
95% confidence
Finding
The keyword coverage section includes expansive everyday writing triggers such as marketing copy, content creation, and title optimization without meaningful constraints, encouraging this exec-enabled skill to match many unrelated prompts. In context, this is more dangerous because the skill exposes read/write/exec tools and background process control, so broad trigger terms can route ordinary user requests into a capability set that can alter system state.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill instructs the agent to launch background processes and kill processes but does not prominently warn about host-side effects, persistence, or the need to confirm before terminating tasks. This is risky because users may not realize the skill can create long-running jobs and manipulate sessions on the system, especially when paired with exec access and ambiguous routing metadata.

Static analysis

No suspicious patterns detected.