AI Investment Analyzer

• Outcome: Review
• Latest audit: May 29, 2026 at 9:30 PM UTC
• Version:
  1.1.1

Overview

This skill is a finance-advice tool that uses mock/simple logic while presenting outputs as real investment analysis, stores analysis history locally, and includes a credential-like publishing token in bundled documentation.

Install only after careful review. Treat outputs as demo-grade information, not financial advice, because the current code does not fetch real market data and uses simplistic logic. The publisher should remove and rotate the exposed token, add clear financial and privacy disclosures, make analysis logging opt-in or visibly documented, and republish with consistent metadata.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill advertises real-time investment analysis and decision support, but the implementation relies entirely on hardcoded prices, fixed trend mappings, and canned risk/ROI outputs. In an investment context, this can materially mislead users into making financial decisions based on fabricated or stale information, especially because the outputs are presented as authoritative analysis.

Description-Behavior Mismatch

Low

• Confidence: 88% confidence
• Finding: The analyze command silently persists user-supplied asset selections and generated analysis results to analysis_log.json without notice. Undisclosed retention of user financial interests can expose sensitive behavioral data and violates user expectations for a simple analysis assistant.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README promotes investment analysis, forecasting, and personalized strategy capabilities without any disclaimer that outputs may be inaccurate and should not be treated as financial advice. In a financial domain, users may rely on generated recommendations for real-world trading decisions, creating foreseeable risk of monetary harm and inappropriate trust in the tool.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The documentation advertises real-time data API integration and multi-user portfolio management but does not explain what financial or personal data may be collected, shared, retained, or exposed. Because portfolio and account-related information is highly sensitive, lack of privacy and data-handling disclosure can lead users to provide confidential data without informed consent or proper safeguards.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill markets investment analysis, forecasts, portfolio optimization, and explicit investment advice without any disclaimer that outputs may be inaccurate, biased, delayed, or unsuitable for a user's financial situation. In a finance context, users may reasonably rely on these outputs for real monetary decisions, creating risk of harmful financial losses and potential regulatory/compliance exposure.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The tool writes persistent logs containing user-supplied asset data and inferred investment interests without any warning, consent flow, or data-handling notice. In the context of an investment assistant, such data may reveal sensitive financial preferences and could be exposed to other local users, backup systems, or later compromise.

VirusTotal

65/65 vendors flagged this skill as clean.