ClawHub
Back to skill

Security audit

AP Daily Report

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises, but it hard-codes local file writes, daily automation, and sending a business PDF to a specific WeChat recipient without a confirmation step.

Install only if you intend reports to be saved to the listed Obsidian directory and sent to the specified WeChat recipient/account on the stated daily schedule. Before use, replace the local path, recipient, accountId, and cron configuration with your own values, and add a manual review step before any external delivery of business analysis.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to write files into a specific local Obsidian vault path on the user's machine without any confirmation, warning, or sandboxing. This creates an unauthorized local file modification risk: an invoked skill could overwrite notes, create persistent artifacts, or leak sensitive business content into an unintended local location.

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill directs the agent to transmit a generated PDF to a specific WeChat recipient and account without a privacy notice, recipient confirmation, or data-classification check. Because the content is a business briefing for a named corporate lead, this can cause unintended disclosure of sensitive internal intelligence to an external messaging channel or the wrong recipient if triggered improperly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/convert-ap-report.mjs:147