ClawHub
Back to skill

Security audit

Remind

Security checks for vulnerabilities and agentic risk

Overview

This reminder skill stores reminder-related preferences locally and has somewhat proactive trigger rules, but the behavior is disclosed, coherent with its purpose, and not paired with executable code or external data transfer.

Before installing, be aware that reminders, preferences, and learned timing may be kept under ~/Clawic/data/remind/. Use it only on a profile where storing personal commitments locally is acceptable, and review or delete that directory if you later want to clear reminder history.

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
  • 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
93% confidence
Finding
The description says to use the skill when the user says phrases like "remind me," "nudge me," "ping me," or "don't let me forget," and also when they merely mention common situations like deadlines, appointments, birthdays, or promises. Several of these cues overlap with ordinary conversation, and the file does not provide explicit exclusion examples at the trigger definition point to narrow when the skill should or should not activate.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly stores user preferences and active reminders in a persistent local directory, but the user-facing description does not clearly warn that personal commitments, deadlines, and habits will be retained. This creates a privacy risk because sensitive personal schedule data may be collected and persisted without sufficiently informed consent, increasing exposure if the host is shared or compromised.

Static analysis

No suspicious patterns detected.