M估值法

• Outcome: Review
• Latest audit: May 29, 2026 at 9:22 PM UTC
• Version:
  1.0.0

Overview

This stock-valuation skill is mostly purpose-focused, but it needs review because it embeds third-party API credentials and relies on external services/helpers in ways users cannot easily control.

Review before installing. The valuation workflow is recognizable, but users should only run it if they accept outbound financial lookups and the publisher replaces embedded API tokens with user-provided configuration, documents the external helper dependency, and removes or clearly labels placeholder financial inputs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: A live-looking Tavily API key is hard-coded directly into the script and exported into the process environment. Anyone with code access can reuse the credential for unauthorized API calls, incur cost, and potentially access associated account data or telemetry.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The script sends stock identifiers and user-supplied names to an external search helper/service without explicit user notice or consent. In an agent-skill context, silent outbound transmission is a real privacy and data-governance risk because users may assume analysis is local.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: A Tushare API token is embedded in code, exposing a reusable credential to anyone who can read the file. Hard-coded service tokens are routinely harvested, abused for quota theft, and can facilitate broader account compromise depending on provider controls.

VirusTotal

65/65 vendors flagged this skill as clean.