ClawHub
Back to skill

Security audit

A Stock Digest

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed A-share stock briefing and alert skill whose local files and scheduled-report behavior match its stated purpose.

Before installing, understand that the skill may guide an agent to run a local Python helper and read or write report files under ~/a-digest. Enable any cron or alert workflow only if you expect automatic market reports, and inspect the referenced local helper script if it exists on your machine.

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
92% confidence
Finding
The skill’s activation criteria are very broad: any request about A-share daily reports, market hotspots, signals, scheduled tasks, or intraday alerts could trigger it. Over-broad invocation increases the chance of unintended execution, especially for autonomous agents, which can lead to unexpected market-analysis actions or report generation without clear user intent.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents local filesystem usage and automated scheduled output generation under ~/a-digest without any disclosure, consent, retention policy, or guardrails. In an agent environment, silent reads/writes and cron-driven report generation can expose local data, create unintended persistence, or overwrite files in ways the user does not expect.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal