A-Share Review and Analyse

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:19 PM UTC
• Version:
  1.0.1

Overview

This skill does the advertised stock-report workflow, including AI analysis and optional publishing, with no evidence of hidden exfiltration or destructive behavior.

Install only if you intend to let this skill fetch market data, call Gemini when a key is configured, write local report/blog files, and create WeChat drafts when WeChat is enabled. Review config.yaml platforms and keep .env files in trusted locations before running.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (19)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill describes capabilities to read environment/config files, write output files, and send network requests, but it does not declare permissions or present clear consent boundaries for those actions. This creates a mismatch between apparent functionality and stated privileges, increasing the chance that an agent executes sensitive file, credential, or network operations without explicit user awareness.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill instructs publishing to Hugo and WeChat and describes external API usage and file creation, but it does not require an explicit warning or confirmation that local content will be written and potentially transmitted to third parties. In a publishing workflow, this can lead to unintended disclosure of generated analysis, metadata, or user-provided content.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill explicitly instructs the agent to publish generated content to Hugo and WeChat, which are write and external-publication actions, but it does not require an explicit user confirmation immediately before those actions occur. This creates a safety gap where an agent could automatically write files or publish drafts containing sensitive, incorrect, or unintended content.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: If no configuration file is found, the code silently creates one on disk in a common project location. This changes the filesystem state without explicit user consent and can normalize insecure defaults or unexpected behavior in automated environments, especially when later execution may publish content externally based on that config.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The code can publish generated content to Hugo and WeChat directly during normal execution based only on configuration, with no explicit runtime confirmation or user-facing disclosure at the action site. In an agent or automation context, this creates a real risk of unintended external publication, data leakage, reputational damage, or abuse if upstream inputs are manipulated.

Credential Access

High

• Category: Privilege Escalation

Content

1. Check if config.yaml exists: `{baseDir}/stock-review/config.yaml`

2. Check if .env file exists and is configured with `GEMINI_API_KEY`, `WECHAT_APP_ID`, `WECHAT_APP_SECRET`: `{baseDir}/stock-review/.env`


**config.yaml supports**: Default publishing platforms | Whether to skip AI analysis by default | Default data backtracking days | Default request delay | Default retry count | API key configuration

• Confidence: 95% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

**config.yaml supports**: Default publishing platforms | Whether to skip AI analysis by default | Default data backtracking days | Default request delay | Default retry count | API key configuration
**.env supports**: API key configuration

**Minimum supported keys** (case-insensitive, accepts `1/0` or `true/false`):

• Confidence: 94% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

url = f"https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={app_id}&secret={app_secret}"
        
        try:
            self.logger.info("Requesting WeChat access token...")
            response = requests.get(url, timeout=10)
            result = response.json()

• Confidence: 93% confidence
• Finding: access token

Unpinned Dependencies

Low

• Category: Supply Chain

Content

akshare>=1.18.0
google-genai>=1.63.0
pandas>=2.0.0
tabulate>=0.9.0

• Confidence: 93% confidence
• Finding: akshare>=1.18.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

akshare>=1.18.0
google-genai>=1.63.0
pandas>=2.0.0
tabulate>=0.9.0
croniter>=6.0.0

• Confidence: 93% confidence
• Finding: google-genai>=1.63.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

akshare>=1.18.0
google-genai>=1.63.0
pandas>=2.0.0
tabulate>=0.9.0
croniter>=6.0.0
google-generativeai>=0.8.0

• Confidence: 93% confidence
• Finding: pandas>=2.0.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

akshare>=1.18.0
google-genai>=1.63.0
pandas>=2.0.0
tabulate>=0.9.0
croniter>=6.0.0
google-generativeai>=0.8.0
markdown>=3.10.0

• Confidence: 90% confidence
• Finding: tabulate>=0.9.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

google-genai>=1.63.0
pandas>=2.0.0
tabulate>=0.9.0
croniter>=6.0.0
google-generativeai>=0.8.0
markdown>=3.10.0
python-dotenv>=1.1.0

• Confidence: 90% confidence
• Finding: croniter>=6.0.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

pandas>=2.0.0
tabulate>=0.9.0
croniter>=6.0.0
google-generativeai>=0.8.0
markdown>=3.10.0
python-dotenv>=1.1.0
pytz>=2025.2

• Confidence: 93% confidence
• Finding: google-generativeai>=0.8.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

tabulate>=0.9.0
croniter>=6.0.0
google-generativeai>=0.8.0
markdown>=3.10.0
python-dotenv>=1.1.0
pytz>=2025.2
requests>=2.32.5

• Confidence: 94% confidence
• Finding: markdown>=3.10.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

croniter>=6.0.0
google-generativeai>=0.8.0
markdown>=3.10.0
python-dotenv>=1.1.0
pytz>=2025.2
requests>=2.32.5
PyYAML>=6.0.0

• Confidence: 90% confidence
• Finding: python-dotenv>=1.1.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

google-generativeai>=0.8.0
markdown>=3.10.0
python-dotenv>=1.1.0
pytz>=2025.2
requests>=2.32.5
PyYAML>=6.0.0

• Confidence: 88% confidence
• Finding: pytz>=2025.2

Unpinned Dependencies

Low

• Category: Supply Chain

Content

markdown>=3.10.0
python-dotenv>=1.1.0
pytz>=2025.2
requests>=2.32.5
PyYAML>=6.0.0

• Confidence: 94% confidence
• Finding: requests>=2.32.5

Unpinned Dependencies

Low

• Category: Supply Chain

Content

python-dotenv>=1.1.0
pytz>=2025.2
requests>=2.32.5
PyYAML>=6.0.0

• Confidence: 95% confidence
• Finding: PyYAML>=6.0.0

VirusTotal

65/65 vendors flagged this skill as clean.