Security audit

Timer

Security checks for vulnerabilities and agentic risk

Overview

This timer skill is not clearly malicious, but it asks agents to run shell commands with user-provided reminder text and the packaged timer implementation is missing.

Review carefully before installing. Only use this in a sandboxed agent, avoid reminder text containing quotes or shell characters, do not rely on it for critical medication/meeting reminders, and expect the package to be incomplete unless the missing timer.js implementation is supplied and audited.

A.I.G

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:65
Finding: Shell command injection risk through user-controlled reminder text
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill description includes a very broad activation cue about project management, team collaboration, and workflow use cases that are unrelated to a timer. Over-broad routing can cause the agent to invoke this skill in inappropriate contexts and expose exec-capable behavior more often than necessary, increasing the chance of misuse or accidental command execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The skill mandates a specific reply format for timer-completion notifications without considering the user's language or accessibility preferences. While not directly enabling code execution, this can cause user confusion, reduce usability, and create delivery failures in multilingual contexts, especially because the skill already contains strict output constraints tied to notification delivery.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The documentation tells users they can set a reminder for a specific wall-clock time using HH:MM:SS, while the rest of the skill only supports relative countdowns. This can cause users to miss time-sensitive events such as meetings or medication reminders because a value like 15:00:00 would be interpreted as a 15-hour countdown instead of 3 PM.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.