ClawHub

Habit Checkin

Security checks across malware telemetry and agentic risk

Overview

This is a simple habit check-in skill that keeps local streak data; its triggers are a bit broad, but the artifacts do not show hidden or harmful behavior.

Install only if you are comfortable with a skill recording habit check-ins to a local JSON file. Consider using explicit habit-related prompts, because generic phrases like "check in", "打卡", or "签到" could cause unintended check-in behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrases include very common expressions such as '打卡', '签到', and 'check in', which can easily occur in unrelated conversations. This can cause the skill to activate unexpectedly and perform persistence-related actions when the user did not intend to use this habit tracker.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The documentation states that the skill uses a persistent local file but does not warn users that invoking the skill may write data to disk. In a context where broad triggers are present, undisclosed persistence increases the risk of silent or unexpected data modification on the host.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal