Stock Analysis

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:41 PM UTC
• Version: 1.0.9

Overview

This skill is a disclosed A-share stock analysis tool that fetches market/news data and uses a configured LLM, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable sending stock queries, retrieved news content, and analysis prompts to your configured LLM and any enabled search/data providers. Use dedicated API keys, avoid confidential research terms in prompts, and prefer a locked dependency environment for production use.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (10)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly documents sending news/search content and full article bodies to external search engines and an LLM, but it does not provide a clear user-facing privacy notice, consent step, or data-handling boundary. In a finance-analysis workflow, user prompts may contain sensitive watchlists, trading interests, or proprietary research context, so undisclosed transmission to third parties creates a real privacy and compliance risk.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The search method sends the raw user query to a third-party endpoint over the network, which can expose potentially sensitive user input to an external service. While this appears to be normal product functionality rather than malicious behavior, it is still a privacy and data-handling risk when users are not clearly informed or when queries may contain confidential terms.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.0.0
efinance>=0.5.0
akshare>=1.10.0
numpy>=1.24.0

• Confidence: 97% confidence
• Finding: The dependency is specified with a lower-bound version only, which allows installation of any future release and makes builds non-reproducible. This increases supply-chain risk because a later vulnerable or breaking version could be pulled in without review.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.0.0
efinance>=0.5.0
akshare>=1.10.0
numpy>=1.24.0
pandas>=2.0.0

• Confidence: 97% confidence
• Finding: The package is unpinned and only constrained by a minimum version, so dependency resolution may select different versions over time. That weakens reproducibility and can silently introduce vulnerable transitive or direct releases into deployments.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.0.0
efinance>=0.5.0
akshare>=1.10.0
numpy>=1.24.0
pandas>=2.0.0
httpx>=0.25.0

• Confidence: 97% confidence
• Finding: Using an open-ended version range for this package means future installs may consume unreviewed releases. In a skill environment that may fetch market or external data, this elevates software supply-chain exposure even though the issue is configuration-level rather than immediately exploitable by itself.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.0.0
efinance>=0.5.0
akshare>=1.10.0
numpy>=1.24.0
pandas>=2.0.0
httpx>=0.25.0
requests>=2.28.0

• Confidence: 98% confidence
• Finding: NumPy is unpinned, so the environment may resolve to different versions across installations and potentially include releases with known security issues. Because there are also advisories associated with this package family, leaving it open-ended makes the dependency risk more significant in context.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

efinance>=0.5.0
akshare>=1.10.0
numpy>=1.24.0
pandas>=2.0.0
httpx>=0.25.0
requests>=2.28.0
python-dotenv>=1.0.0

• Confidence: 97% confidence
• Finding: The pandas dependency is not fixed to a single reviewed version, allowing environment drift and possible installation of releases with security concerns. Given that this package has had security-related advisories, the open-ended requirement increases risk beyond a purely operational issue.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

akshare>=1.10.0
numpy>=1.24.0
pandas>=2.0.0
httpx>=0.25.0
requests>=2.28.0
python-dotenv>=1.0.0

• Confidence: 98% confidence
• Finding: httpx is specified with only a minimum version, so builds may pull in different releases over time. Since this is a network-facing HTTP client and advisories exist for the package, unpinned resolution can directly affect request handling security and reliability.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy>=1.24.0
pandas>=2.0.0
httpx>=0.25.0
requests>=2.28.0
python-dotenv>=1.0.0

• Confidence: 98% confidence
• Finding: Requests is unpinned, which enables uncontrolled upgrades and non-reproducible installs. Because requests is a core HTTP client with multiple historical advisories, this increases the chance of inheriting a vulnerable version or behavior in production.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

pandas>=2.0.0
httpx>=0.25.0
requests>=2.28.0
python-dotenv>=1.0.0

• Confidence: 95% confidence
• Finding: python-dotenv is not pinned to a single version, so future installs may bring in unreviewed releases. While lower impact than network-facing libraries, it still creates supply-chain and reproducibility risk, especially where environment files may contain secrets.

VirusTotal

67/67 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.