uzi-skill-stock-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Retrieves financial data and market sentiment from established third-party services including yfinance, DuckDuckGo, and Chinese financial platforms like EastMoney and Xueqiu.
  • [EXTERNAL_DOWNLOADS]: Downloads core skill code and required libraries from the vendor's GitHub repository during installation.
  • [COMMAND_EXECUTION]: Executes internal Python scripts and manages the environment using standard system commands such as pip, python, and git.
  • [COMMAND_EXECUTION]: Provides a 'remote mode' feature that initiates a Cloudflare Tunnel to allow users to view reports on mobile devices via a temporary public URL.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from web search results and financial news feeds, which represents an indirect prompt injection surface.
  • Ingestion points: DuckDuckGo search results and various financial API responses.
  • Boundary markers: Not explicitly defined in the skill instructions.
  • Capability inventory: Execution of local Python scripts, network operations for data fetching, and file writing for report assembly.
  • Sanitization: No explicit content sanitization or validation logic is detailed in the skill markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 01:41 AM