Stock Watcher v2

• Outcome: Review
• Latest audit: May 27, 2026, 5:07 AM
• Version:
  2.3.0

Overview

This stock-alert skill mostly matches its stated purpose, but it disables HTTPS certificate verification and can run recurring stock-data pushes, so it needs review before installation.

Review before installing. Use only if you are comfortable with recurring stock watchlist monitoring and push delivery, replace any bundled push target with your own, and remove or fix the SSL certificate bypass before relying on the reported market data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Context-Inappropriate Capability

High

• Confidence: 99% confidence
• Finding: The code globally disables HTTPS certificate verification by replacing the default SSL context with an unverified one. This makes all HTTPS requests in the process vulnerable to man-in-the-middle interception or tampering, allowing an attacker on the network path to alter stock data or inject malicious responses despite the use of HTTPS.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The README promotes scheduled multi-channel stock notifications and external data fetching but does not clearly warn that user-selected stock lists, identifiers, and generated reports may be transmitted through third-party channels or services. In this skill context, automated push delivery to WeChat/Telegram/Discord increases the risk of unintended disclosure of personal trading interests or account-linked identifiers, especially when run on a schedule without ongoing user review.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The manifest uses broad trigger phrases like '设置股票提醒' and '盯盘推送', which can easily appear in ordinary conversation and cause accidental activation. Because this skill can create scheduled behavior and perform repeated scans, unintended invocation is more risky than a simple read-only utility skill.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill description highlights stock tracking features but does not clearly warn users that it stores tracking history to CSV and can create recurring scheduled tasks. Hidden persistence and background execution reduce informed consent and can leave ongoing data collection or repeated actions running longer than the user expects.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: Certificate validation is disabled silently, with no warning to users that the reported market data may be fetched over connections that are not authenticated. In this skill's context, that increases the chance users act on spoofed or manipulated financial information, which is especially problematic for a stock-monitoring tool that users may trust for timely decisions.

VirusTotal

66/66 vendors flagged this skill as clean.