Security audit

Prayer Times Skill

Security checks across malware telemetry and agentic risk

Overview

This is a coherent prayer-times and journaling skill, with disclosed local storage and a disclosed prayer-time API, but users should understand the privacy and reminder limitations.

Install only if you are comfortable with city names being sent to aladhan.com and with your location, todos, journal entries, and reminder settings being saved locally in OpenClaw memory. Do not rely on the advertised Telegram reminders unless the publisher implements actual scheduling and notification delivery.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill advertises Bash/runtime capabilities and file/network behavior but does not clearly declare the permissions those actions require. In an agent ecosystem, undeclared shell capability reduces transparency and can cause the skill to be invoked with more power than users or reviewers expect, increasing the chance of unsafe execution or policy bypass.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The documented purpose understates important behaviors: sending user location data to a third-party API, persisting user content locally, and overstating reminder functionality. This is dangerous because users may disclose sensitive location or journal data without informed consent, and operators may approve the skill under an incomplete understanding of its real data flows and side effects.

Intent-Code Divergence

Medium

Confidence: 98% confidence
Finding: The reminder feature makes concrete claims about Telegram notifications and prayer reminders, but the code only writes a local JSON flag and never schedules jobs or sends messages. This is a security-relevant integrity issue because users may rely on reminders for time-sensitive religious obligations while the feature silently does nothing.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README explicitly documents persistent storage of sensitive user-generated data such as journal entries, todos, location, and reminder settings, but provides no privacy notice, retention explanation, or guidance on securing or deleting that data. Because journal and location data can reveal highly personal habits, beliefs, and routines, silent local retention increases the risk of unintended disclosure on shared or compromised systems.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The documentation states that prayer schedules are fetched from the aladhan.com API, which implies user location or city queries may be transmitted to a third-party service, but it does not warn users about that external disclosure. This matters because location requests can expose a user's approximate whereabouts, routine, and religious practice to an outside provider without informed consent.

Vague Triggers

Medium

Confidence: 78% confidence
Finding: The invocation scope includes the vague trigger 'Islamic productivity,' which can cause the skill to activate for broad, loosely related requests. Over-broad routing is risky because it may collect or store user data such as todos, journals, or location in situations where the user did not specifically ask for this skill.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill states it uses aladhan.com but does not provide a clear privacy warning that user-supplied location data is sent to an external service. Location can be sensitive personal data, and the lack of upfront disclosure undermines informed consent and creates avoidable privacy risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.